Method, apparatus, and recording medium for estimating sales opportunity of item

Abstract

The present disclosure relates to a method, electronic apparatus, and recording medium for estimating a sales opportunity. The method according to an embodiment of the present disclosure may include the steps of: determining, on the basis of scenario selection criteria, at least one sales scenario corresponding to an item among one or more sales scenarios related to sales of the item; determining at least one prediction model corresponding to the at least one sales scenario among one or more prediction models related to prediction of a sales opportunity; determining, on the basis of the item and the at least one prediction model, one or more pieces of attribute information to be applied to the at least one prediction model; and calculating an expected sales volume of the item on the basis of the at least one prediction model and the one or more pieces of attribute information.

Description

Method, device and recording medium for calculating sales opportunities for items

[0001] The present disclosure relates to a technique for predicting or calculating sales opportunities of items in an e-commerce service.

[0002] Recent advancements in communications technology have led to the widespread adoption of e-commerce services, which allow for the trading of goods (items) online. Furthermore, information and communication technologies are being introduced into the transportation, logistics, and inventory management industries related to e-commerce services to improve operational efficiency.

[0003] Meanwhile, accurately calculating sales information is essential for effectively operating e-commerce services. In particular, information on Gross Merchandise Value (GMV) is a crucial indicator for e-commerce service providers. Similarly, information on lost GMV, resulting from lost sales opportunities, can also be used as a key indicator for decision-making regarding e-commerce services. Lost sales opportunities can occur, for example, when an item is out of stock. Even if a user is willing to purchase an item, sales cannot be generated if the item is out of stock, resulting in the loss of potential sales opportunities. In this case, lost sales opportunities can be calculated based on information about expected sales if the item were not out of stock.

[0004] However, if the sales patterns for each period and item being forecasted are not reflected, actual sales patterns may differ from the forecasts, resulting in errors. Therefore, a solution to this problem is needed.

[0005] A technical problem to be solved through one embodiment of the present disclosure is to accurately predict sales opportunities for items in an e-commerce service.

[0006] Another technical problem to be solved through one embodiment of the present disclosure relates to calculating sales opportunities by considering sales patterns by item and period in an e-commerce service.

[0007] Another technical challenge to be addressed by one embodiment of the present disclosure is to reflect item-specific bias in predicting sales opportunities in e-commerce services.

[0008] The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art of the present disclosure from the description below.

[0009] A method for calculating a sales opportunity of an item performed by an electronic device according to one embodiment of the present disclosure may include: determining at least one sales scenario corresponding to the item based on a scenario selection condition among one or more sales scenarios regarding sales of the item; determining at least one prediction model corresponding to the at least one sales scenario among one or more prediction models regarding prediction of sales opportunities; determining one or more characteristic information to be applied to the at least one prediction model based on the item and the at least one prediction model; and calculating an expected sales amount of the item based on the at least one prediction model and the one or more characteristic information.

[0010] In one embodiment, the method may further include calculating an expected loss sales amount of the item based on the calculated expected sales amount and out-of-stock information corresponding to the item.

[0011] In one embodiment, the out-of-stock information may include information regarding the length of time that the item remains in an out-of-stock state.

[0012] In one embodiment, the method may further include calculating an expected loss sales corresponding to the item based on the expected loss sales amount and price information of the item.

[0013] In one embodiment, the method may include: calculating an expected sales amount corresponding to an item group based on an expected sales amount corresponding to each of a plurality of items included in the item group; calculating an actual sales amount corresponding to the item group based on an actual sales amount corresponding to each of the plurality of items; and calculating total error information corresponding to the item group based on the expected sales amount corresponding to the item group and the actual sales amount corresponding to the item group.

[0014] In one embodiment, the total error information may be calculated based on a weighted mean absolute percentage error (WMAPE) value between the actual sales and the predicted sales corresponding to the item group.

[0015] In one embodiment, the method may further include: calculating total error information corresponding to all items remaining from among the plurality of items except for the first item in the item group; and calculating an error contribution of the first item based on the total error information corresponding to all of the remaining items and the total error information corresponding to the item group.

[0016] In one embodiment, the step of determining the sales scenario may include the step of determining whether one or more scenario selection conditions corresponding to each of the one or more sales scenarios are satisfied based on at least some of item information, timing information, sales-related information, out-of-stock information, and promotion information; and the step of determining at least one sales scenario corresponding to the item based on whether the one or more scenario selection conditions are satisfied.

[0017] In one embodiment, for each of the one or more sales scenarios, a priority for each scenario is assigned, and whether a scenario selection condition corresponding to each of the sales scenarios is satisfied can be sequentially determined based on the priority for each scenario.

[0018] In one embodiment, the method may further include calculating prediction bias information corresponding to the item; and calculating a corrected predicted sales amount corresponding to the item based on the predicted sales amount and the predicted bias information.

[0019] In one embodiment, the prediction bias information may be calculated based on the error between the predicted sales amount and the actual sales amount corresponding to the item.

[0020] In one embodiment, the prediction bias information may be identified based on a sum of errors corresponding to overprediction and a sum of errors corresponding to underprediction among one or more error information corresponding to one or more dates.

[0021] In one embodiment, the step of calculating the expected sales amount may include a step of calculating the expected sales amount by date, and the step of checking the predicted bias information may further include a step of calculating the actual sales amount corresponding to the item by date corresponding to the expected sales amount; and a step of calculating the predicted bias information corresponding to the item by date based on the actual sales amount and the predicted sales amount corresponding to the item.

[0022] An electronic device according to one embodiment of the present disclosure comprises: one or more processors; one or more memories storing instructions to be executed by the one or more processors; and when the instructions are executed by the one or more processors, the one or more processors may be configured to execute a method according to the present disclosure.

[0023] In a non-transitory computer-readable recording medium having recorded thereon instructions that, when executed by one or more processors according to one embodiment of the present disclosure, cause the one or more processors to perform operations, the instructions may be configured to cause the one or more processors to perform a method according to the present disclosure.

[0024] According to the present disclosure, it is possible to relatively accurately predict sales opportunities for items in an e-commerce service.

[0025] According to the present disclosure, sales opportunity calculation can be performed in consideration of sales patterns by item and period in an e-commerce service.

[0026] According to the present disclosure, item-specific bias can be reflected in the prediction of sales opportunities in e-commerce services.

[0027] The effects according to the technical idea of ​​the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the specification.

[0028] FIG. 1 illustrates an environment in which an electronic device according to one embodiment of the present disclosure can be applied.

[0029] FIG. 2 is a block diagram of an electronic device according to one embodiment of the present disclosure.

[0030] FIG. 3 is a flowchart illustrating a method for calculating the expected sales volume of an item according to one embodiment of the present disclosure.

[0031] FIG. 4 is a diagram illustrating one or more scenario consideration factors for determining scenario selection conditions according to one embodiment of the present disclosure.

[0032] FIG. 5 is a flowchart illustrating a method for determining a sales scenario according to one embodiment of the present disclosure.

[0033] FIG. 6 is a flowchart illustrating a method for calculating a corrected expected sales amount according to one embodiment of the present disclosure.

[0034] FIG. 7a and FIG. 7b are drawings for more specifically explaining the method for calculating sales opportunities and adjusted sales opportunities described with reference to FIG. 3 and FIG. 6.

[0035] The various embodiments described in this disclosure are exemplified for the purpose of clearly explaining the technical concept of this disclosure and are not intended to be limited to specific embodiments. The technical concept of this disclosure includes various modifications, equivalents, alternatives, and embodiments selectively combined from all or part of the embodiments described in this disclosure. Furthermore, the scope of the technical concept of this disclosure is not limited to the various embodiments presented below or the specific descriptions thereof.

[0036] Terms used in this disclosure, including technical or scientific terms, unless otherwise defined, may have the meaning commonly understood by a person of ordinary skill in the art to which this disclosure belongs.

[0037] The expressions "includes," "may include," "comprises," "may have," "have," and "may have" used in this disclosure indicate the presence of a target feature (e.g., a function, operation, or component), but do not exclude the presence of other additional features. In other words, such expressions should be understood as open-ended terms that imply the possibility of including other embodiments.

[0038] The singular expressions used in this disclosure may include the plural meaning unless the context clearly indicates otherwise, and the same applies to the singular expressions set forth in the claims.

[0039] The expressions "first," "second," or "first", "second", etc. used in this document, unless the context indicates otherwise, are used to refer to multiple similar objects and to distinguish one object from another, and do not limit the order or importance among the objects.

[0040] As used herein, the expressions "A, B, and C", "A, B, or C", "A, B, and / or C", or "at least one of A, B, and C", "at least one of A, B, or C", "at least one of A, B, and / or C", etc., may refer to each of the listed items or to all possible combinations of the listed items. For example, "at least one of A or B" may refer to (1) at least one A, (2) at least one B, (3) at least one A and at least one B.

[0041] The expression "based on" as used in this disclosure is used to describe one or more factors that influence a decision, act of judgment, or action described in a phrase or sentence containing this expression, and this expression does not exclude additional factors that influence the decision, act of judgment, or action.

[0042] As used herein, the expression that a component (e.g., a first component) is “connected” or “connected” to another component (e.g., a second component) may mean that the component is directly connected or connected to the other component, as well as connected or connected via a new other component (e.g., a third component).

[0043] The expression "configured to" used in the present disclosure may have the meanings of "set to", "having the ability to", "modified to", "made to", "capable of", etc., depending on the context. This expression is not limited to the meaning of "specifically designed in hardware", and for example, a processor configured to perform a specific operation may mean a general purpose processor that can perform the specific operation by executing software, or a special purpose computer that is structured through programming to perform the specific operation.

[0044] Hereinafter, various embodiments of the present disclosure will be described with reference to the attached drawings. In the attached drawings and the description of the drawings, identical or substantially equivalent components may be assigned the same reference numerals. Furthermore, in the description of various embodiments below, duplicate descriptions of identical or corresponding components may be omitted, but this does not mean that such components are not included in the embodiments.

[0045] FIG. 1 illustrates an environment in which an electronic device according to an embodiment of the present disclosure can be applied. FIG. 1 illustrates an environment in which an electronic device according to an embodiment of the present disclosure can be applied. An electronic device (110) and a database (120) are connected via a network and can communicate with each other. Here, communication between the electronic device (110) and the database (120) may mean that the electronic device (110) communicates with a database management system (DBMS) that manages the database (120). In other words, the electronic device (110) can access the database (120) via a network.

[0046] The electronic device (110) may be a device for predicting sales opportunities for items in an e-commerce service. The e-commerce service may, for example, include a sales platform that sells one or more items online. The electronic device (110) may be any server device, including a server device that manages the e-commerce service, or any electronic device, including an electronic device that manages inventory in the e-commerce service. As another example, the electronic device (110) may be implemented as a terminal capable of transmitting and receiving various information to and from a database (120) via a network. For example, the electronic device (110) may be one of a computer, a laptop, a portable communication terminal (such as a smartphone), a portable multimedia device, a wearable device, or an HMD. However, the type of the electronic device (110) is not limited thereto, and the electronic device (110) may be any device that includes an input / output interface capable of receiving information from a user or outputting information to a user, and that can communicate with the database (120) or other devices via a network. The electronic device (110) may utilize information stored in the database (120) to predict sales opportunities for an item. In one embodiment, the sales opportunities being predicted may include information regarding the potential likelihood of sales for the item, such as at least some of the item's expected sales, expected lost sales, and expected lost sales for the item.

[0047] The electronic device (110) can provide various types of information regarding sales opportunity prediction to the user and receive input regarding sales opportunity prediction from the user. Specifically, the electronic device (110) can obtain a command regarding sales opportunity prediction from the user through an input / output interface, perform a sales opportunity prediction in response to the obtained command, and output the results of the sales opportunity calculation to the user or store them in the electronic device (110), transmit them to another device, etc. The input obtained from the user can include various forms of input, such as a click using a mouse, a touch using a touchpad or a touch screen, voice recognition, other electronic input, or a voice input using a microphone. The output of the electronic device (110) can include various forms of output, such as a visual form through a display, a projector, a hologram, etc., or an auditory form through a speaker, etc.

[0048] The database (120) can store information that serves as the basis for calculating sales opportunities for items in an e-commerce service. For example, the database (120) can store sales logs for each item handled in the e-commerce service. Furthermore, for example, the sales logs for each item in the database (120) can be updated in real time or repeatedly, either periodically or aperiodically. The electronic device (110) can obtain information regarding daily sales volume of any item through the database (120). For example, information regarding sales volume by period (e.g., date) of a specific item, all items handled in the e-commerce service, or items satisfying specific conditions among all items handled in the e-commerce service can be obtained. Furthermore, information regarding sales volume by time zone, day, week, month, quarter, year, or certain period can also be obtained for any item.

[0049] The network may serve to connect the electronic device (110) with the database (120) or other external devices. For example, the network may provide a connection path so that the electronic device (110) can be connected to the database (120) and transmit and receive packet data with the database (120). The network may be implemented as any type of wired or wireless network, such as a local area network (LAN), a wide area network (WAN), a mobile radio communication network, or Wibro (Wireless Broadband Internet).

[0050] Another example of an environment in which an electronic device according to another embodiment of the present disclosure can be applied, and which is not illustrated, is an electronic device (110) that may include a database. In this case, information stored in the database can be obtained without using the network illustrated in FIG. 1. In this case, the electronic device (110) may also include a database management system (DBMS) that manages the database.

[0051] FIG. 2 is a block diagram of an electronic device (200) according to one embodiment of the present disclosure. The electronic device (200) can process information regarding the estimation of sales opportunities for items. In one embodiment, the electronic device (200) may include one or more processors (210), one or more memories (220), and a communication interface (230) as components. In one embodiment, at least one of the components of the electronic device (200) may be omitted, or another component may be added to the electronic device (200). In one embodiment, additionally or alternatively, some of the components may be implemented in an integrated manner or implemented as a single or multiple entities. In the present disclosure, one or more processors (210) may be referred to as a processor (210). The expression “processor (210)” may mean a set of one or more processors, unless the context clearly indicates otherwise. In the present disclosure, one or more memories (220) may be referred to as a memory (220). The expression "memory (220)" may mean a set of one or more memories, unless the context clearly indicates otherwise. In one embodiment, at least some of the components inside / outside the electronic device (200) may be connected to each other via a bus, a General Purpose Input / Output (GPIO), a Serial Peripheral Interface (SPI), or a Mobile Industry Processor Interface (MIPI), and may exchange information (data, signals, etc.).

[0052] The processor (210) may control at least one component of the electronic device (200) connected to the processor (210) by running software (e.g., commands, programs, etc.). In addition, the processor (210) may perform various operations such as calculations, processing, data generation, and processing related to the present disclosure. In addition, the processor (210) may load data, etc. from the memory (220) or store data in the memory (220). Furthermore, the processor (210) may transmit and receive various information with the database (120) through the communication interface (230). In one embodiment, the processor (210) may control the communication interface (230) to request various information regarding sales opportunity calculation from the database (120) and receive various information regarding sales opportunity calculation from the database (120).

[0053] The memory (220) can store various information (data). The information stored in the memory (220) is information acquired, processed, or used by at least one component of the electronic device (200), and may include software (e.g., commands, programs, etc.). The memory (220) may include volatile and / or non-volatile memory. In the present disclosure, the commands or programs are software stored in the memory (220), and may include an operating system for controlling the resources of the electronic device (200), an application, and / or middleware for providing various functions to the application so that the application can utilize the resources of the electronic device (200). In one embodiment, the memory (220) may store commands that, when executed by the processor (210), cause the processor (210) to perform operations. The memory (220) may store at least a portion of information received from a database via the communication interface (230) and / or information transmitted to the database via the communication interface (230). Specifically, the memory (220) can store information regarding sales opportunity prediction of an item and commands executed by the processor (210).

[0054] The communication interface (communication interface, 230) can perform wireless or wired communication between the electronic device (200) and a database or other external electronic device. For example, the communication interface (230) can perform wireless communication according to a method such as eMBB (enhanced Mobile Broadband), URLLC (Ultra Reliable Low-Latency Communications), MMTC (Massive Machine Type Communications), LTE (Long-Term Evolution), LTE-A (LTE Advance), NR (New Radio), UMTS (Universal Mobile Telecommunications System), GSM (Global System for Mobile communications), CDMA (Code Division Multiple Access), WCDMA (Wideband CDMA), WiBro (Wireless Broadband), WiFi (Wireless Fidelity), Bluetooth (Bluetooth), NFC (Near Field Communication), GPS (Global Positioning System), or GNSS (Global Navigation Satellite System). For example, the communication interface (230) may perform wired communication according to a method such as Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), Recommended Standard-232 (RS-232), or Plain Old Telephone Service (POTS). In one embodiment, the electronic device (200) may be implemented by being integrated with another device. In this case, the communication interface (230) may function as a connection circuit or interface connecting the electronic device (200) and the other device.

[0055] Hereinafter, the operations described as being performed by the electronic device in FIGS. 3 to 7b can be understood as being performed by the processor (210) of the electronic device (200) described in FIG. 2.

[0056] FIG. 3 is a flowchart illustrating a method for calculating the expected sales volume of an item according to one embodiment of the present disclosure.

[0057] Hereinafter, with reference to FIG. 3, the description will proceed assuming that the operations of a method for calculating the expected sales volume of an item according to one embodiment of the present disclosure are performed by the electronic device (110) illustrated in FIG. 1. Furthermore, for convenience of explanation, the subject of the operations included in the method may be omitted; however, unless otherwise indicated in the context, it may be interpreted that the operations are performed by the electronic device (110).

[0058] In operation S301, the electronic device (110) can determine a sales scenario corresponding to the item.

[0059] A sales scenario may refer to a classification of expected sales patterns, sales trends, or user purchasing patterns for a particular item.

[0060] In one embodiment, the sales scenarios may include one or more scenarios classified through methods such as learning, regression analysis, categorical analysis, or identified based on heuristic methods.

[0061] For example, a sales scenario may include a scenario regarding the sales pattern of a promoted item. In an example of a sales scenario for a promoted item, if a promotion for a specific item is scheduled within a certain period of time (e.g., 35 days) from the predicted time, the electronic device (110) may determine that the selected scenario condition corresponding to the sales scenario of the promoted item is satisfied. Accordingly, the electronic device (110) may predict that the sales pattern of the specific item will correspond to the sales scenario of the promoted item, and may predict the sales volume of the item based on the sales pattern. The electronic device (110) may receive various information from the database (120) to determine whether the scenario selection condition is satisfied. Various sales scenarios and scenario selection conditions are described later with reference to FIGS. 5 and 6 .

[0062] In one embodiment, a sales scenario may be determined based on scenario selection criteria. The electronic device (110) may determine whether the scenario selection criteria are satisfied based on one or more scenario consideration factors. The scenario consideration factors may include at least some of item information, timing information, sales-related information, out-of-stock information, and promotional information.

[0063] In one embodiment, the scenario selection conditions may include one or more conditions corresponding to each of one or more sales scenarios. For each sales scenario, a priority may be assigned. The electronic device (110) may sequentially determine whether the scenario selection conditions corresponding to each of one or more sales scenarios are satisfied based on the priority assigned to each scenario.

[0064] In operation S302, the electronic device (110) can determine a prediction model corresponding to the sales scenario.

[0065] In one embodiment, the electronic device (110) may determine one or more predictive models corresponding to a selected sales scenario from among one or more predictive models for predicting sales opportunities. The predictive models may include one or more models that provide predictions regarding sales opportunities for an item.

[0066] In one embodiment, one or more predictive models may correspond to each sales scenario. In one embodiment, the electronic device (110) may store information regarding the correspondence between each sales scenario and one or more predictive models corresponding to the sales scenario. The electronic device (110) may identify the predictive model corresponding to the sales scenario determined in operation S301.

[0067] In operation S303, the electronic device (110) can determine characteristic information to be applied to the prediction model.

[0068] In one embodiment, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the prediction model based on the item and the determined prediction model. The one or more characteristic pieces of information may include information to be input into the prediction model to predict sales opportunities. The characteristic pieces may be determined in response to the determined prediction model.

[0069] In one embodiment, the characteristic information may include at least some information corresponding to the prediction model, including item information, timing information, sales-related information, out-of-stock information, and promotional information. In one embodiment, the characteristic information may include at least some of the scenario consideration factors used to determine scenario selection conditions. The electronic device (110) may store information regarding the correspondence between sales scenarios and characteristic information.

[0070] In operation S304, the electronic device (110) can calculate the expected sales amount of the item based on the prediction model and characteristic information.

[0071] In one embodiment, characteristic information may be used to train a predictive model and / or predict sales opportunities using the predictive model. For example, the electronic device (110) may input values ​​of one or more characteristic information corresponding to a determined predictive model, and predict sales opportunities based on a prediction method or algorithm corresponding to each predictive model.

[0072] In one embodiment, the electronic device (110) may learn one or more parameters included in the predictive model based on a learning algorithm. The electronic device (110) may learn one or more parameter values ​​included in the predictive model based on characteristic information. In this case, the values ​​of one or more characteristic information may include past sales data, or may include some data extracted from past sales data based on specified conditions, or data processed from past sales data. For example, the specified conditions may include conditions regarding at least some of item information, timing information, sales-related information, out-of-stock information, and promotional information.

[0073] In one embodiment, the forecast of sales opportunities may include at least some of the following: estimating expected sales, estimating expected lost sales, and estimating expected lost revenue. For example, estimating expected sales for an item can be understood as a forecast of potential future sales opportunities in an e-commerce service.

[0074] In one embodiment, the estimated lost sales for an item may be calculated based on the estimated sales and out-of-stock information. The estimated expected sales for an item can be understood as a lost sales opportunity during the time the item is out of stock. Therefore, the electronic device (110) may calculate the estimated lost sales based on the estimated sales and out-of-stock information. The out-of-stock information may include, for example, information regarding the ratio of the duration of the out-of-stock status of the predicted item to the period of time for which the sales volume is predicted. The out-of-stock information may be calculated based on the duration of the out-of-stock status and the total period of time for which the sales volume is predicted. For example, if the sales volume is predicted daily, the out-of-stock information may be calculated as the ratio of the duration of the out-of-stock status on that day to the total time (e.g., 24 hours) of the predicted date.

[0075] In one embodiment, the expected loss sales of an item may be calculated based on the expected loss sales volume and the item's price information. For example, the expected loss sales of an item may be calculated by multiplying the expected loss sales volume and the item's price information.

[0076] In one embodiment, the predictive model may include one or more predictive methods or predictive algorithms. The one or more predictive methods or predictive algorithms may include any method or algorithm known in the art. For example, the predictive model may include an algorithm comprising at least some or a combination of the following: a Light Gradient-Boosting Machine (Light GBM), a Moving Average model, a weighted Moving Average model, a Holt-Winters model, and an Auto-Regressive Integrated Moving Average with Exogenous Variables (ARIMAX).

[0077] The electronic device (110) can estimate sales opportunities based on a predictive model and characteristic information. For example, the electronic device (110) can input actual values ​​corresponding to characteristic information into the predictive model as input data, and predict sales opportunities based on a predictive algorithm.

[0078] Referring to FIGS. 4 and 5 below, the operation (S301) of determining a sales scenario described with reference to FIG. 3 and the operation (S302) of determining a prediction model corresponding to the sales scenario will be described in more detail.

[0079] FIG. 4 is a diagram illustrating one or more scenario consideration factors for determining scenario selection conditions according to one embodiment of the present disclosure.

[0080] Referring to Table (400) of Scenario Consideration Elements in FIG. 4, the scenario consideration elements may include at least some of item information, timing information, sales-related information, out-of-stock information, and promotional information. The scenario consideration elements may include one or more elements that may influence the sales pattern of an item.

[0081] In one embodiment, item information may include various information about the item. Item information may include the item's category and at least some of the item's attributes. The item's category may be classified into one or more categories (e.g., a first category, a second category, a third category, a fourth category, and a fifth category).

[0082] In one embodiment, the attributes of an item may include at least some of order status, stocking period, selling period, seasonality, and holiday characteristics.

[0083] In one embodiment, the order status may include various information regarding the order of an item. An order for an item can be understood as a process for purchasing an item from a supplier and storing it in stock for sale to customers in an e-commerce service. The order status may include at least some of the following: whether the item has been ordered, the order date, the order quantity, whether the order has been completed, whether the order has been canceled, and whether the item has been received after the order has been completed.

[0084] In one embodiment, the stocking period may include information regarding the period during which an item for sale was received in a storage facility, warehouse, fulfillment center, etc. For example, the stocking period may correspond to the period from the first stocking to the last stocking for the same item.

[0085] In one embodiment, the sale period may correspond to the period from the time a particular item was first sold to the time it was last sold.

[0086] In one embodiment, seasonality may correspond to the characteristic that an item's sales volume is affected by the season. The seasonality of an item may be determined based on a correlation between the item and temperature, calculated based on historical sales data and temperature data for each period. Seasonality may include, for example, at least some information about whether the item's sales volume is affected by the season (whether seasonality exists) and the season that affects the item's sales volume. For example, if an item has the characteristic of high sales during the "summer" period and low sales during other seasons, the seasonality of the item may be "summer." In this case, the "season" in "seasonality" does not necessarily refer to the four meteorological seasons, such as spring, summer, fall, and winter. Seasonality may refer to a characteristic that fluctuates over a period of time, such as the rainy season, the beginning of the year, and the end of the year.

[0087] In one embodiment, a holiday attribute may refer to an attribute that affects an item's sales volume on holidays. The holiday attribute may include at least some information about whether the holiday attribute exists and about specific holidays that affect the item's sales volume. For example, if an item's sales surge only during the Chuseok holiday period, the holiday attribute for that item may be "Chuseok."

[0088] In one embodiment, the timing information may include actual sales data that can be used to predict sales opportunities, or information indicating attributes of a time period corresponding to the period for which sales opportunities are to be predicted. The timing information may include at least some of the following: week of the year, week of the month, season, day of the week, date of the month, holiday information, seasonal information, and promotional schedule information. In one embodiment, the timing information may correspond to a specific date or period, and multiple timing information may correspond to a specific date or period.

[0089] Week of year can refer to the week number of a specific time period within the same year. Week of month can refer to the week number of a specific time period within the same month.

[0090] In one embodiment, sales-related information may include at least some of sales volume information, price information, sales summary information, and restock notification information. The sales summary information may include key information about sales for a specific item or over a specific period. For example, it may include at least some information about average sales, top-selling items, top-selling items, and inventory levels. Restock notification information may include information about whether a specific item is available for restock.

[0091] In one embodiment, the out-of-stock information may include the out-of-stock period. The out-of-stock period may refer to the period during which a specific item remains out-of-stock due to lack of stock. The out-of-stock period may refer to the percentage of time the item remains out-of-stock within a reference period. For example, if one day is used as the reference period and the item remains out-of-stock for six hours, the out-of-stock period may be expressed as a percentage, such as 0.25 or 25%, representing the percentage of six hours in a day (24 hours).

[0092] In one embodiment, promotion information may include at least some of the promotion type and promotion details. Promotion types may include various types, such as promotions that discount an item by a certain amount, promotions that discount an item by a certain percentage, promotions that issue coupons, promotions that utilize rewards, seasonal promotions, regular promotions, and promotions for preferred customers. Promotion details may include various information about the promotion, such as the promotion period, the promotion discount rate, the category of items eligible for the promotion, and the category of customers eligible for the promotion.

[0093] In one embodiment, the electronic device (110) may determine whether a scenario selection condition is satisfied based on one or more scenario consideration factors.

[0094] FIG. 5 is a flowchart illustrating a method for determining a sales scenario according to one embodiment of the present disclosure.

[0095] Hereinafter, with reference to FIG. 5, the description will proceed assuming that the operations of a method for determining a sales scenario according to one embodiment of the present disclosure are performed by the electronic device (110) illustrated in FIG. 1. Furthermore, for convenience of explanation, the subject of the operations included in the method may be omitted; however, unless otherwise indicated in the context, it may be interpreted that the operations are performed by the electronic device (110).

[0096] In operation S501, the electronic device (110) can determine whether one or more scenario selection conditions corresponding to each of one or more sales scenarios are satisfied.

[0097] In one embodiment, the electronic device (110) may determine whether a first scenario condition, a second scenario condition, or a third scenario condition is satisfied in response to a first scenario, a second scenario, or a third scenario among the sales scenarios.

[0098] In one embodiment, the electronic device (110) can determine whether a first scenario condition, a second scenario condition, or a third scenario condition is satisfied based on a scenario consideration factor.

[0099] In one embodiment, the first scenario may include a scenario corresponding to a new item. A new item may refer to a newly released item or an item that was not previously sold but has now begun sales. Items corresponding to new items may have similar sales patterns, and such patterns may be classified as scenarios corresponding to new items. The electronic device (110) may check at least some information among the scenario consideration factors to determine whether the first scenario condition corresponding to the first scenario is satisfied. Whether the first scenario condition is satisfied may be determined based on the creation date of the item information. For example, if the target period for predicting a sales opportunity and the item are within a specified period (e.g., 30 days) from the creation date of the item information for the corresponding item, the electronic device (110) may determine that the first scenario condition is satisfied. To determine whether the first scenario condition is satisfied, the electronic device (110) may receive, from the database, information on the period and item information among the scenario consideration factors.

[0100] In one embodiment, the electronic device (110) may further check sales-related information to determine whether the first scenario condition is satisfied. The first scenario condition may be determined based on at least some of the following: whether the initial sales occurred within the specified period from the creation date of the item information, in addition to whether the target time (e.g., the current point in time or the target date of the prediction) falls within a specified period from the creation date of the item information; and whether restocking notification information exists within the specified period. For example, if item information is created as a new item but a specified period has passed since then, it may not be appropriate to predict sales opportunities for the item based on the sales pattern of the new item. Similarly, if no sales have occurred until the specified period has passed, it may not be appropriate to predict sales for the item based on the sales pattern corresponding to the new item.

[0101] In one embodiment, the second scenario may include a scenario corresponding to aging items. Aging items may include items that are sensitive to trends or the latest technology, items with a rapid release cycle for new products, or items that tend to experience declining sales volume as inventory ages. For example, smartphones have a rapid release cycle for new products and are sensitive to the latest technology, so sales volume may decline rapidly as inventory ages. Items that fall under the category of aging items may have similar sales patterns, and such patterns can be classified as scenarios corresponding to aging items. The electronic device (110) may check at least some information among the scenario consideration factors to determine whether the second scenario conditions are satisfied. Whether the second scenario conditions are satisfied may be determined based on at least some of the order status, sales volume information, and the delivery period. For example, whether the second scenario conditions are satisfied may be determined based on whether sales volume has decreased by a threshold value after a certain period of time based on past sales volume information. For another example, the electronic device (110) may check the order status and determine whether the second scenario condition is satisfied based on whether an order exists after a certain period of time. As another example, the electronic device (110) may determine that the second scenario condition is satisfied if the sales volume decreases by a threshold value after a certain period of time and no orders exist after a certain period of time. To determine whether the second scenario condition is satisfied, the electronic device (110) may receive order information and sales volume information from the database among the scenario consideration factors.

[0102] In one embodiment, the third scenario may include a scenario corresponding to a slow-moving item. A slow-moving item may refer to an item with a low turnover rate, i.e., an item that tends to remain in inventory due to slow sales or low demand. Items corresponding to a slow-moving item may have similar sales patterns, and such patterns may be classified as a scenario corresponding to a slow-moving item. The electronic device (110) may check at least some information among the scenario consideration factors to determine whether the third scenario condition corresponding to the third scenario is satisfied. Whether the third scenario condition is satisfied may be determined based on price information, sales volume information, and / or item attributes (e.g., stocking period). For example, the third scenario condition may include whether the price of the item is above a specified threshold price. If the price of the item is high, demand may be low, leading to a lower turnover rate. As another example, the third scenario condition may include whether the sales volume of the item has been below a specified threshold sales volume during a specified past period. For example, based on the period to be predicted, if sales less than the critical sales amount occurred during a specified period in the past (e.g., 3 weeks) or the number of days (days) on which sales occurred is less than the critical number of days, the electronic device (110) may determine that the third scenario condition is satisfied. As another example, whether the third scenario condition is satisfied may be determined based on the period of time during which the item was received. Whether the third scenario condition is satisfied may be determined based on whether the first time of receipt of the item is after a specified period (e.g., 60 days) from the predicted date. In order to determine whether the third scenario condition is satisfied, the electronic device (110) may receive period information and item information from the database among the scenario consideration factors.

[0103] In one embodiment, the electronic device (110) may determine whether a scenario selection condition is satisfied based on the priority of each scenario. For example, in order to predict the sales volume of an item, the electronic device (110) may first determine whether a first scenario condition is satisfied, and if the first scenario condition is satisfied, the electronic device (110) may proceed to operation S502 to select a first prediction model. If the first scenario condition is not satisfied, the electronic device (110) may determine whether a second scenario condition corresponding to the next priority of the first scenario is satisfied. Thereafter, if the second scenario condition is satisfied, the electronic device (110) may proceed to operation S502 to select a second prediction model. If the second scenario condition is not satisfied, the electronic device (110) may determine whether a third scenario condition corresponding to the next priority of the second scenario is satisfied. Thereafter, if the third scenario condition is satisfied, the electronic device (110) may proceed to operation S502 to select a third prediction model. If the third scenario condition is not satisfied, the electronic device (110) may proceed to operation S503. If the first scenario condition, the second scenario condition, and the third scenario condition are all not satisfied, the electronic device (110) may proceed to operation S503.

[0104] In operation S502, the electronic device (110) can select the first prediction model, the second prediction model, or the third prediction model based on whether the first scenario condition, the second scenario condition, or the third scenario condition is satisfied.

[0105] In one embodiment, the first prediction model corresponding to the first scenario may include a weighted moving average model algorithm. When the electronic device (110) corresponds to the first scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the first prediction model. The one or more characteristic pieces of information corresponding to the first prediction model may include at least a portion of scenario consideration factors. The one or more characteristic pieces of information to be applied to the first prediction model may include, for example, at least a portion of item information, timing information, sales information, and out-of-stock information. In one embodiment, the electronic device (110) may generate, update, or learn the first prediction model by updating one or more parameters to be applied to the algorithm of the first prediction model based on existing prediction data and past sales information regarding one or more items corresponding to the same scenario (the first scenario). The electronic device (110) may calculate the expected sales amount of the item based on the first prediction model and the one or more characteristic pieces of information.

[0106] In one embodiment, the second prediction model corresponding to the second scenario may include a Moving Average model algorithm. When the electronic device (110) corresponds to the second scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the second prediction model. The one or more characteristic pieces of information corresponding to the second prediction model may include at least a portion of scenario consideration factors. The one or more characteristic pieces of information to be applied to the second prediction model may include, for example, at least a portion of order status, item information, timing information, sales information, and out-of-stock information. In one embodiment, the electronic device (110) may generate, update, or learn the second prediction model by updating one or more parameters to be applied to the algorithm of the second prediction model based on existing prediction data and past sales information regarding one or more items corresponding to the same scenario (the second scenario). The electronic device (110) may calculate the expected sales amount of the item based on the second prediction model and the one or more characteristic pieces of information.

[0107] In one embodiment, the third prediction model corresponding to the third scenario may include a Moving Average model algorithm. When the electronic device (110) corresponds to the third scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the third prediction model. The one or more characteristic pieces of information corresponding to the third prediction model may include at least a portion of scenario consideration factors. The one or more characteristic pieces of information to be applied to the third prediction model may include, for example, at least a portion of a stocking period, item information, timing information, sales volume information, and out-of-stock information. In one embodiment, the electronic device (110) may generate, update, or learn the third prediction model by updating one or more parameters to be applied to the algorithm of the third prediction model based on existing prediction data and past sales volume information regarding one or more items corresponding to the same scenario (the third scenario). The electronic device (110) may calculate the expected sales volume of the item based on the third prediction model and the one or more characteristic pieces of information.

[0108] In operation S503, the electronic device (110) can determine whether the fourth scenario is satisfied.

[0109] In one embodiment, the electronic device (110) may determine whether a condition of the fourth scenario is satisfied in response to the fourth scenario among the sales scenarios.

[0110] In one embodiment, the electronic device (110) can determine whether the fourth scenario condition is satisfied based on the scenario consideration factors.

[0111] In one embodiment, the fourth scenario may include a scenario corresponding to a promotional item. A promotional item may refer to an item scheduled for promotion. Items corresponding to promotional items may have similar sales patterns, and such patterns may be classified as scenarios corresponding to promotional items. The electronic device (110) may check at least some information among the scenario consideration factors to determine whether the fourth scenario condition corresponding to the fourth scenario is satisfied. Whether the fourth scenario condition is satisfied may be determined based on whether a promotion is scheduled within a specified period after the predicted date from the predicted date. For example, based on the target time and item for predicting sales opportunities, if promotion schedule information exists within a specified period (e.g., 35 days) after the target time of the prediction, and if the target time of the prediction is during the promotion period, the fourth scenario condition may be determined to be satisfied. The electronic device (110) may determine whether the fourth scenario condition is satisfied based on at least some of the item attributes, promotion schedule information, and promotion information among the scenario consideration factors. The electronic device (110) may receive item properties, promotion schedule information, and promotion information from the database (120) among the scenario consideration factors to determine whether the fourth scenario condition is satisfied. If the fourth scenario condition is satisfied, the electronic device (110) may proceed to operation S504, and if the fourth scenario condition is not satisfied, the electronic device (110) may proceed to operation S508.

[0112] In operation S504, the electronic device (110) can determine whether the fifth scenario condition, the second scenario condition, or the seventh scenario condition is satisfied in response to the fifth scenario, the sixth scenario, or the seventh scenario among the sales scenarios.

[0113] In one embodiment, the electronic device (110) may determine whether the fifth scenario condition, the sixth scenario condition, or the seventh scenario condition is satisfied based on the scenario consideration factors. The fifth scenario may include a scenario corresponding to an item with holiday characteristics. The sixth scenario may include a scenario corresponding to an item with seasonal characteristics. The seventh scenario may include a scenario corresponding to an item with both holiday characteristics and seasonal characteristics. In this case, the fourth scenario, i.e., the scenario corresponding to a promotional item, the fifth scenario, the sixth scenario, and the seventh scenario may all include a characteristic in which sales patterns vary depending on the time of year. Furthermore, in the case of promotions, there is a high possibility that promotions will be accompanied by specific periods, such as holidays or seasons, and predicting sales opportunities based on sales patterns that reflect holiday characteristics, seasonality, etc. along with promotions can increase the likelihood of more accurate predictions. Therefore, in operation S504, the electronic device (110) may determine whether the fifth scenario condition, the sixth scenario condition, or the seventh scenario condition is satisfied if the fourth scenario condition is satisfied.

[0114] In one embodiment, the fifth scenario may include a scenario corresponding to an item with a holiday characteristic. An item with a holiday characteristic may refer to an item whose sales volume fluctuates significantly based on whether it is a specific holiday. For example, for an item that has high sales only during the Chuseok holiday period and low sales during other periods, the fifth scenario corresponding to the holiday characteristic may be applied. Items corresponding to the holiday characteristic may have similar sales patterns, and such patterns may be classified into the fifth scenario corresponding to the holiday characteristic. The electronic device (110) may check at least some information among the scenario consideration factors to determine whether the fifth scenario condition is satisfied. Whether the fifth scenario condition is satisfied may be determined based on whether the item has a holiday characteristic and whether the holiday is scheduled within a specified period (e.g., 35 days) after the predicted date. For example, based on the target period for sales opportunity prediction and the item's attributes, the fifth scenario condition may be determined to be satisfied if the item has a holiday characteristic and holiday information exists within a specified period (e.g., 35 days) after the target period for sales opportunity prediction. In one embodiment, the electronic device (110) may determine whether the fifth scenario condition is satisfied based on whether the corresponding holiday information and holiday characteristics are of a corresponding type of holiday. For example, among the scenario consideration factors, the holiday characteristics and holiday information may each include information regarding the type of the corresponding holiday (e.g., Lunar New Year, Chuseok, Christmas). The electronic device (110) may determine whether the fifth scenario condition is satisfied based on at least some of the holiday characteristics and holiday information among the scenario consideration factors.The electronic device (110) can receive holiday characteristics and holiday information from the database among the scenario consideration factors to determine whether the fifth scenario condition is satisfied.

[0115] In one embodiment, the sixth scenario may include a scenario corresponding to seasonal items. A seasonal item may refer to an item whose sales volume fluctuates significantly depending on whether it falls within a specific season. For example, for an item that has high sales volume only during the summer and low sales volume during other periods, the sixth scenario corresponding to seasonal items may be applied. Items corresponding to seasonal items may have similar sales patterns, and such patterns may be classified into the sixth scenario corresponding to seasonal items. The electronic device (110) may check at least some information among the scenario consideration factors to determine whether the sixth scenario condition is satisfied. Whether the sixth scenario condition is satisfied may be determined based on whether the item is seasonal and whether a specific season is expected within a specified period (e.g., 35 days) after the predicted date. For example, based on the target period for sales opportunity prediction and the attributes of the item, the sixth scenario condition may be determined to be satisfied if the item is seasonal and season information exists within a specified period (e.g., 35 days) after the target period for the prediction. In one embodiment, the electronic device (110) may determine whether the sixth scenario condition is satisfied based on whether the season corresponding to the seasonal information and the seasonality are of a corresponding type of season. For example, among the scenario consideration factors, the seasonality and season information may each include information regarding the type of the corresponding season (e.g., spring, summer, fall, winter, rainy season, dry season, rainy season, specific season, white night, polar night, weather). The electronic device (110) may determine whether the sixth scenario condition is satisfied based on at least some of the seasonality and season information among the scenario consideration factors.The electronic device (110) can receive seasonality and seasonal information from the database among the scenario consideration factors to determine whether the sixth scenario condition is satisfied.

[0116] In one embodiment, the seventh scenario may include a scenario corresponding to an item having both a holiday characteristic and a seasonal characteristic. Items corresponding to items having both a holiday characteristic and a seasonal characteristic may have similar sales patterns, and such patterns may be classified into the seventh scenario corresponding to items having both a holiday characteristic and a seasonal characteristic. The electronic device (110) may determine that the seventh scenario condition is satisfied if a specific season and a specific holiday occur simultaneously within a specified period (e.g., 35 days) from the period being predicted, and if the item's properties include both seasonal and holiday characteristics. The electronic device (110) may check at least some information among the scenario consideration factors to determine whether the seventh scenario condition corresponding to the fifth scenario is satisfied. Whether the seventh scenario condition is satisfied may be determined based on whether the item has a holiday characteristic, whether the item has seasonality, and whether a specific holiday and a specific season are scheduled simultaneously within a specified period from the prediction date to the prediction date. For example, based on the time period and the attributes of the item to be predicted for a sales opportunity, if the item has seasonality and holiday characteristics, and seasonal information and holiday information exist within a specified period (e.g., 35 days) after the time period to be predicted, the seventh scenario condition may be determined to be satisfied. The electronic device (110) may determine whether the seventh scenario condition is satisfied based on at least some of the seasonality, seasonal information, holiday characteristics, and holiday information among the scenario consideration factors. In order to determine whether the seventh scenario condition is satisfied, the electronic device (110) may receive the seasonality, seasonal information, holiday characteristics, and holiday information among the scenario consideration factors from the database.

[0117] In one embodiment, scenario priorities may not be applied among the fifth scenario condition, the sixth scenario condition, and the seventh scenario condition. In operation S504, the electronic device (110) may simultaneously determine whether the fifth scenario condition, the sixth scenario condition, and the seventh scenario condition are satisfied, or may determine whether these conditions are satisfied in any order and indiscriminately.

[0118] In operation S504, if the electronic device (110) satisfies the fifth scenario condition, the sixth scenario condition, or the seventh scenario condition, it may proceed to operation S505.

[0119] In operation S504, if the electronic device (110) does not satisfy the fifth scenario condition, the sixth scenario condition, or the seventh scenario condition, the electronic device (110) may proceed to operation S507.

[0120] In operation S505, the electronic device (110) can compare the predicted results. Operation S505 can be performed when the fourth scenario condition is satisfied and any one of the fifth scenario condition, the sixth scenario condition, and the seventh scenario condition is satisfied.

[0121] In one embodiment, the electronic device (110) may calculate a prediction result (hereinafter, referred to as a first prediction result) corresponding to a specified period (e.g., 35 days) based on a fourth prediction model corresponding to the fourth scenario. In addition, the electronic device (110) may calculate a prediction result (hereinafter, referred to as a second prediction result) corresponding to the same specified period (e.g., 35 days) as the fourth prediction model based on a prediction model corresponding to a scenario that satisfies a scenario determination condition among the fifth, sixth, and seventh scenarios, i.e., the fifth, sixth, or seventh prediction models. The electronic device (110) may compare the first prediction result and the second prediction result during the specified period (e.g., 35 days). The comparison of the prediction results may include, for example, a comparison between average values ​​of the prediction results during the specified period, or a comparison between corresponding partial periods during the specified period. For example, if the specified period is 35 days and the first prediction result and the second prediction result include prediction results for each day, the prediction results of the first prediction result and the second prediction result can be compared for each day.

[0122] In operation S506, the electronic device (110) may select a fourth prediction model or a mixed model based on the comparison of the prediction results in operation S505. The electronic device (110) may select the fourth prediction model if the first prediction result calculated based on the fourth prediction model is greater than the first prediction result for the entire specified period. Alternatively, the electronic device (110) may select a mixed model in which at least some of the fifth, sixth, and seventh prediction models are mixed with the fourth prediction model if the second prediction result calculated based on the fifth, sixth, and seventh prediction models is greater than the first prediction result for the entire specified period, or if there is a period in which the second prediction result is greater than the first prediction result for at least a portion of the specified period. The mixed model may include at least some of a mixed model of the fourth and fifth prediction models, a mixed model of the fourth and sixth prediction models, and a mixed model of the fourth and seventh prediction models. A hybrid model may refer to a model that performs predictions based on characteristic information that combines at least some of the parameters of each prediction model, or the entire characteristic information of the models being mixed. The electronic device (110) may select an algorithm to be applied, update or learn parameters, and determine characteristic information to be used for prediction, depending on the type of each hybrid model.

[0123] In operation S507, the electronic device (110) may select a fourth prediction model.

[0124] In one embodiment, the fourth prediction model corresponding to the fourth scenario may include at least some of a Light Gradient-Boosting Machine (Light GBM) algorithm and an Autoregressive Integrated Moving Average with Exogenous Variables (ARIMAX) algorithm. When the electronic device (110) corresponds to the fourth scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the fourth prediction model. The one or more characteristic pieces of information corresponding to the fourth prediction model may include at least some of the scenario consideration factors. The one or more characteristic pieces of information to be applied to the fourth prediction model may include at least some of item characteristics, timing information, sales information, out-of-stock information, and promotion information, for example. In one embodiment, the electronic device (110) may generate, update, or learn the fourth prediction model by updating one or more parameters to be applied to the algorithm of the fourth prediction model based on existing prediction data and past sales information regarding one or more items corresponding to the same scenario (the fourth scenario). The electronic device (110) can calculate the expected sales amount of an item based on the fourth prediction model and one or more characteristic pieces of information.

[0125] In operation S508, the electronic device (110) may determine whether the fifth scenario condition, the second scenario condition, or the seventh scenario condition is satisfied in response to the fifth, sixth, or seventh scenario among the sales scenarios. Operation S508 may include at least a part of operation S504.

[0126] In operation S508, if the electronic device (110) satisfies the fifth scenario condition, the sixth scenario condition, or the seventh scenario condition, it may proceed to operation S509.

[0127] In operation S508, if the electronic device (110) does not satisfy the fifth scenario condition, the sixth scenario condition, or the seventh scenario condition, the electronic device (110) may proceed to operation S510.

[0128] In operation S509, the electronic device (110) may select the fifth prediction model, the sixth prediction model, or the seventh prediction model based on whether the fifth scenario condition, the sixth scenario condition, or the seventh scenario condition is satisfied.

[0129] In one embodiment, the fifth prediction model corresponding to the fifth scenario may include the Holt-Winters algorithm. When the electronic device (110) corresponds to the fifth scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the fifth prediction model. The one or more characteristic pieces of information corresponding to the fifth prediction model may include at least a portion of scenario consideration factors. The one or more characteristic pieces of information to be applied to the fifth prediction model may include, for example, at least a portion of item attributes, timing information, timing information, sales information, and out-of-stock information. In one embodiment, the electronic device (110) may generate, update, or learn the fifth prediction model by updating one or more parameters to be applied to the algorithm of the fifth prediction model based on existing prediction data and past sales information regarding one or more items corresponding to the same scenario (the fifth scenario). The electronic device (110) may calculate the expected sales of the item based on the fifth prediction model and the one or more characteristic pieces of information.

[0130] In one embodiment, the sixth prediction model corresponding to the sixth scenario may include at least some of the Light Gradient-Boosting Machine (Light GBM) algorithm and the Holt-Winters algorithm. When the electronic device (110) corresponds to the sixth scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the sixth prediction model. The one or more characteristic pieces of information corresponding to the sixth prediction model may include at least some of the scenario consideration elements. The one or more characteristic pieces of information to be applied to the sixth prediction model may include, for example, at least some of item attributes, timing information, sales information, out-of-stock information, sales summary information, seasonal information, and price information. In one embodiment, the electronic device (110) may generate, update, or learn the sixth prediction model by updating one or more parameters to be applied to the algorithm of the sixth prediction model based on existing prediction data and past sales information regarding one or more items corresponding to the same scenario (the sixth scenario). The electronic device (110) may calculate the expected sales of the item based on the sixth prediction model and the one or more characteristic pieces of information.

[0131] In one embodiment, the seventh prediction model corresponding to the seventh scenario may include at least a portion of the Holt-Winters algorithm. When the electronic device (110) corresponds to the seventh scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the seventh prediction model. The one or more characteristic pieces of information corresponding to the seventh prediction model may include at least a portion of scenario consideration factors. The one or more characteristic pieces of information to be applied to the seventh prediction model may include, for example, at least a portion of item attributes, time information, sales information, out-of-stock information, sales summary information, holiday information, seasonal information, and price information. In one embodiment, the electronic device (110) may generate, update, or learn the seventh prediction model by updating one or more parameters to be applied to the algorithm of the seventh prediction model based on existing prediction data and past sales information regarding one or more items corresponding to the same scenario (the seventh scenario). The electronic device (110) may calculate the expected sales of an item based on the seventh prediction model and the one or more characteristic pieces of information.

[0132] In operation S510, the electronic device (110) may determine that the period and item to be predicted correspond to a general sales scenario among the sales scenarios. A general sales scenario may refer to a sales scenario that does not correspond to the first through seventh scenarios.

[0133] In operation S511, the electronic device (110) may select a default prediction model corresponding to a general sales scenario.

[0134] In one embodiment, the basic prediction model may include a Light GBM (Light Gradient-Boosting Machine) algorithm. When the electronic device (110) corresponds to a general sales scenario, the electronic device (110) may determine one or more characteristic pieces of information to be applied to the basic prediction model. The one or more characteristic pieces of information corresponding to the basic prediction model may include at least a portion of scenario consideration elements. The one or more characteristic pieces of information to be applied to the basic prediction model may include, for example, at least a portion of item attributes, timing information, sales-related information, and out-of-stock information. Specifically, the characteristic pieces of information corresponding to the basic prediction model may include at least a portion of order status, stocking period, and sales period among item attributes. The characteristic pieces of information corresponding to the basic prediction model may include at least a portion of week within the year, week within the month, day of the week, and day within the month among period information. In one embodiment, the electronic device (110) may generate, update, or learn the basic prediction model by updating one or more parameters to be applied to the algorithm of the basic prediction model based on existing prediction data and past sales information regarding one or more items corresponding to the same scenario (general sales scenario). The electronic device (110) can calculate the expected sales amount of an item based on a basic prediction model and one or more characteristic pieces of information.

[0135] FIG. 6 is a flowchart illustrating a method for calculating a corrected expected sales amount according to one embodiment of the present disclosure.

[0136] Hereinafter, with reference to FIG. 6, the description will proceed assuming that the operations of a method for calculating a corrected expected sales volume according to one embodiment of the present disclosure are performed by the electronic device (110) illustrated in FIG. 1. Furthermore, for convenience of explanation, the subject of the operations included in the method may be omitted; however, unless otherwise indicated in the context, it may be interpreted that the operations are performed by the electronic device (110).

[0137] In operation S601, the electronic device (110) may calculate prediction bias information corresponding to an item. The prediction bias information may include information regarding the tendency of the predicted result value corresponding to the item to exhibit an error relative to the actual value. For example, the prediction bias information may be calculated based on the error between the item's expected sales volume and actual sales volume.

[0138] In one embodiment, the electronic device (110) may calculate an expected sales amount corresponding to each of a plurality of items included in an item group. An item group may refer to a group including a plurality of items, and the plurality of items may be classified based on various criteria including the category of the items. The electronic device (110) may calculate an expected sales amount corresponding to each of the plurality of items. The electronic device (110) may determine a sales scenario corresponding to each of the plurality of items, and calculate an expected sales amount for each of the plurality of items based on a respective prediction model corresponding to the determined sales scenario. The electronic device (110) may calculate an actual sales amount corresponding to the item group based on the expected sales amount for each of the plurality of items belonging to the item group.

[0139] In one embodiment, the electronic device (110) may calculate actual sales corresponding to each of a plurality of items included in an item group. The electronic device (110) may receive data from the database (120) regarding the estimated sales corresponding to each of the plurality of items and the actual sales of each of the plurality of items during a corresponding period, and may calculate the actual sales corresponding to the item group.

[0140] In one embodiment, the electronic device (110) may calculate error information corresponding to an item group based on the expected sales volume and actual sales volume corresponding to the item group. The error information corresponding to the item group may be expressed as aggregated error information.

[0141] In one embodiment, the electronic device (110) may calculate evaluation information regarding a prediction model based on total error information corresponding to an item group. The evaluation information regarding the prediction model may include an indicator of the performance of the prediction model. For example, if an item group includes multiple items for which predictions are performed based on the same prediction model, the electronic device (110) may determine that a model with a lower total error information corresponding to the item group has higher performance. The electronic device (110) may perform predictions based on different prediction models for the same item group and select a prediction model more suitable for the item group based on the total error information. For example, in order to improve the performance of the prediction model, the electronic device (110) may compare total error information calculated based on a modified prediction model, such as one with different parameters or different characteristic information, with the total error information of an existing prediction model, and update the parameters of the prediction model.

[0142] In one embodiment, the total error information may be calculated based on a Weighted Mean Absolute Percentage Error (WMAPE) value between the actual sales and the predicted sales corresponding to the item group. The WMAPE may be calculated based on a weighted average of the absolute values ​​of the relative errors of the predicted sales of each item relative to the actual sales, with the actual sales corresponding to the item group as the weight for each item, and the ratio of the actual sales of each item to the sum of the actual sales. The WMAPE is described in detail in FIGS. 7A and 7B .

[0143] In one embodiment, the electronic device (110) may calculate total error information corresponding to all items in an item group, excluding a specific item (e.g., a first item). The electronic device (110) may calculate total error information corresponding to all items in the item group, excluding the first item, based on the weighted absolute average error between the actual sales volume and the expected sales volume for the remaining items in the item group.

[0144] In one embodiment, the electronic device (110) may calculate the error contribution of the first item based on the total error information corresponding to the item group and the total error information corresponding to all items in the item group except the first item. The error contribution may refer to the ratio of the error that the predicted value of a specific item (e.g., the first item) has with respect to the actual value to the total error of the entire item group. The error contribution of the first item may be calculated based on the difference between the total error information corresponding to the item group and the total error information corresponding to all items in the item group except the first item. The error contribution may have a negative value, and it may be understood that the smaller the error contribution of a specific item (e.g., the first item) has, the more accurately the prediction for the specific item (e.g., the first item) is made.

[0145] In one embodiment, the electronic device (110) may classify error information into errors corresponding to overprediction and errors corresponding to underprediction. Overprediction may refer to an error that occurs when the predicted sales volume is greater than the actual sales volume. The error corresponding to overprediction may be calculated based on the weighted absolute average error between the actual sales volume and the predicted sales volume calculated when overprediction occurs. Underprediction may refer to an error that occurs when the predicted sales volume is less than the actual sales volume. The error corresponding to underprediction may be calculated based on the weighted absolute average error between the actual sales volume and the predicted sales volume calculated when underprediction occurs. The electronic device (110) may classify error information corresponding to overprediction and error corresponding to underprediction among error information calculated for each of a plurality of items included in an item group.

[0146] In one embodiment, the electronic device (110) may calculate total prediction bias information corresponding to a group of items. The total prediction bias information may be calculated based on a weighted absolute mean error regarding the difference between error information corresponding to overprediction and error information corresponding to underprediction among error information corresponding to each item calculated for the group of items.

[0147] In one embodiment, the electronic device (110) may calculate the expected sales volume of an item for each of multiple time periods. The period may refer to the period for which the expected sales volume is to be calculated. For example, if the target period is one day, the multiple time periods may refer to multiple dates. In this case, the electronic device (110) may calculate the expected sales volume for each of the multiple dates. When calculating the expected sales volume for a single item for multiple dates, the expected sales volume may be calculated based on different prediction models for each date. For example, for predictions for a specific date among multiple dates, the fourth scenario may be applied based on promotional information. However, for predictions for other dates, the general sales scenario may be applied since promotions are not applied. In this case, different sales scenarios may be determined for the same item, and the expected sales volume may be calculated based on different prediction models for each date.

[0148] In one embodiment, the electronic device (110) may calculate error information corresponding to each of the plurality of periods based on the estimated sales amount calculated corresponding to each of the plurality of periods and the actual sales amount calculated corresponding to each of the plurality of periods.

[0149] In one embodiment, the electronic device (110) can classify error information of a specific item (e.g., a first item) calculated for each of a plurality of periods for the item into an error corresponding to an overprediction and an error corresponding to an underprediction.

[0150] In one embodiment, the prediction bias information corresponding to an item may be calculated based on a weighted absolute average error of the difference between error information corresponding to overprediction and error information corresponding to underprediction among error information of the item calculated corresponding to each of a plurality of periods.

[0151] In one embodiment, prediction bias information may correspond to each item. Even when predicting sales opportunities for the same item, the corresponding prediction models may differ for each period depending on the scenario selection conditions. For example, even for the same item, the satisfaction of the scenario selection conditions may vary depending on the period, resulting in different corresponding prediction models. The prediction bias information may be at least one of data reflecting the bias of the prediction values ​​corresponding to each item and the bias of the prediction values ​​corresponding to each prediction model.

[0152] In operation S601, the electronic device (110) can calculate the corrected expected sales volume.

[0153] In one embodiment, the electronic device (110) can adjust the predicted results of a sales opportunity based on the predicted bias information. The predicted sales volume can be adjusted to reflect the predicted bias information. The electronic device (110) can calculate the adjusted predicted loss sales volume based on the adjusted predicted sales volume. The electronic device (110) can calculate the adjusted expected loss sales volume based on the adjusted predicted loss sales volume.

[0154] In one embodiment, the adjusted forecast sales volume may be calculated by adding a correction value based on forecast bias information to the forecast sales volume. The forecast bias information may include information regarding a bias ratio, and the correction value may be calculated as the product of the bias ratio and the forecast sales volume.

[0155] FIG. 7a and FIG. 7b are drawings for more specifically explaining the method for calculating sales opportunities and adjusted sales opportunities described with reference to FIG. 3 and FIG. 6.

[0156] In FIG. 7a, a method for calculating sales opportunities and adjusted sales opportunities is specifically described based on an example table (701) regarding sales opportunities, which shows projected sales and actual sales corresponding to a plurality of dates (20230101 and 20230102) as examples for a plurality of periods, and an item group including a first item, a second item, and a third item as examples for a plurality of items.

[0157] In Fig. 7b, a method for calculating sales opportunities and corrected sales opportunities based on an error calculation example table (702) showing error information and prediction bias information calculated based on the sales opportunity example table (701) of Fig. 7a is specifically described.

[0158] Referring to Figure 7a, the expected sales volume of the sales opportunity example table (701) can be calculated for each item and each period (by date). At this time, the expected lost sales volume can be calculated based on the expected sales volume and out-of-stock information. The expected sales volume can be substituted into Mathematical Formula 1 (710). "Lost Unit" in Mathematical Formula 1 (710) may represent the expected lost sales volume, and "Forecast" may represent the expected sales volume. The "OOS rate" in Mathematical Formula 1 (710) may include information regarding the ratio of the period during which the predicted item remains out-of-stock relative to the period (e.g., one day) for which the sales volume is predicted. For example, referring to the sales opportunity example table (701), the period to be forecasted is a specific date (“20230103”) and the out-of-stock time is “12 hours”, so the corresponding “OOS rate” may be the ratio of 12 hours to 24 hours (a day), i.e., “0.5”.

[0159] Referring to FIG. 7a, the expected lost sales volume can be substituted into Equation 2 (720). In Equation 2 (720), "Lost GMV" may be the expected lost sales volume, and "Price" may refer to the price of the item.

[0160] Referring to FIG. 7A, error information can be calculated based on mathematical expression 3 (730), an error corresponding to overprediction can be calculated based on mathematical expression 4 (740), and an error corresponding to underprediction can be calculated based on mathematical expression 5 (750). In addition, prediction bias information can be calculated based on mathematical expression 6 (760). At this time, "i" may be an index corresponding to each item, and "n" may be the final value of the item index. For example, in the example of FIG. 7A, the values ​​"1", "2", and "3" may be assigned to the index values ​​("i") of the first item, the second item, and the third item, respectively, and the value "3" may be assigned to "n" corresponding to the final value of the item index. At this time, "A i" may be the actual sales corresponding to the item index "i", and "F i " may be the expected sales amount corresponding to the item index "i" ("Forecast" in mathematical expression 1 (710)).

[0161] Referring to FIG. 7B, the calculation example table (702) may include results calculated for all items included in the item group among the results calculated based on the numerical values ​​included in the sales opportunity example table (701) of FIG. 7A and mathematical equations 1 (710), 2 (720), 3 (730), 4 (740), 5 (750), and 6 (760). The total error information (77%) for the entire item group corresponding to the date "20230101" may be calculated by substituting the expected sales amount and actual sales amount corresponding to "20230101" of each of the first item, the second item, and the third item into mathematical equation 3 (730). Through the same method, based on mathematical expressions 3 (730), 4 (740), and 5 (750), the total error information (45%) corresponding to the date "20230102", the total overprediction error (73%) corresponding to the date "20230101", the total underprediction error (5%) corresponding to the date "20230101", and the total prediction bias information (68%) corresponding to the date "20230101" can be calculated, and the total error information (80%) corresponding to all items except the first item corresponding to the date "20230101" can be calculated. At this time, for the total error information corresponding to all items except the first item, only "2" and "3" excluding "1" corresponding to the first item can be substituted into the item index "i" of mathematical expression 3 (730).

[0162] Referring to FIG. 7b, the error contribution (-3%) of the first item corresponding to the date “20230101” can be calculated as the difference between the total error (77%) of all items excluding the first item corresponding to “20230101” and the total error (80%) of all items excluding the first item.

[0163] Referring to FIG. 7b, the prediction bias information (-11%) corresponding to the first item in the period "20230101" to "20230102" can be calculated by applying different indices for each date to the first item in mathematical expression 6 (760) described with reference to FIG. 7a, and inputting the expected sales and actual sales. That is, "1" can be input to the index "i" for the expected sales and actual sales of the first item in "20230101", and "2" can be input to the index "i" for the expected sales and actual sales of the first item in "20230102".

[0164] Referring to FIG. 7b, the predicted bias information (-11%) calculated for the first item is applied to the expected loss sales (15) of the first item, so that the corrected expected loss sales of the first item can be calculated as "13.39", which is the result of "15+{(-11%)*15}". Here, "{(-11%)*15}" may refer to the correction value explained with reference to FIG. 6. Subsequently, the corrected expected loss sales of the first item can be multiplied by the price information to calculate the corrected expected loss sales (66.96).

[0165] In the flowcharts according to the present disclosure, each step of the method or algorithm is described in a sequential order. However, the steps may be performed in any order that can be arbitrarily combined, in addition to being performed sequentially. The description of the flowcharts or flowcharts of the present disclosure does not exclude changes or modifications to the method or algorithm, and does not imply that any step is essential or desirable. In one embodiment, at least some of the steps may be performed in parallel, iteratively, or heuristically. In another embodiment, at least some of the steps may be omitted, or other steps may be added.

[0166] Various embodiments according to the present disclosure may be implemented as software on a machine-readable storage medium. The software may be software for implementing various embodiments described in the present disclosure. The software may be inferred from various embodiments described in the present disclosure by programmers skilled in the art to which the present disclosure pertains. For example, the software may be a program including machine-readable instructions (e.g., instructions, codes, or code segments). The device may be a device capable of operating according to instructions called from a storage medium, such as a computer. In one embodiment, the device may be a computing device according to various embodiments described in the present disclosure. In one embodiment, the processor of the device may execute the called instructions, causing components of the device to perform functions corresponding to the instructions. The storage medium may refer to any type of recording medium that stores data and can be read by the device. The storage medium may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, etc. In one embodiment, the storage medium may be implemented in a distributed form, such as in a network-connected computer system. In this case, the software may be distributed, stored, and executed in the computer system. In another embodiment, the storage medium may be a non-transitory storage medium. A non-transitory storage medium refers to a tangible medium that exists regardless of whether data is stored semi-permanently or temporarily, and does not include signals that are transmitted transitively.

[0167] While the technical concepts of the present disclosure have been described through various embodiments, it should be understood that the technical concepts of the present disclosure encompass various substitutions, modifications, and variations that can be made within the scope of those skilled in the art to which the present disclosure pertains. Furthermore, it should be understood that such substitutions, modifications, and variations are encompassed within the scope of the appended claims.

Claims

1. In the method of calculating sales opportunities for items performed by electronic devices, A step of determining at least one sales scenario corresponding to the item based on a scenario selection condition among one or more sales scenarios regarding the sales of the item; A step of determining at least one predictive model corresponding to at least one sales scenario among one or more predictive models for predicting sales opportunities; A step of determining one or more characteristic information to be applied to the at least one prediction model based on the above item and the at least one prediction model; and A method for calculating sales opportunities, comprising the step of calculating the expected sales amount of the item based on the at least one predictive model and the one or more characteristic pieces of information.

2. In paragraph 1, A sales opportunity calculation method further comprising a step of calculating an expected loss sales amount of the item based on the calculated expected sales amount and out-of-stock information corresponding to the item.

3. In paragraph 2, A method for calculating sales opportunities, wherein the above out-of-stock information includes information about the time that the item has been in an out-of-stock state.

4. In paragraph 2, A sales opportunity calculation method further comprising the step of calculating the expected loss sales corresponding to the item based on the expected loss sales volume and the price information of the item.

5. In paragraph 1, A step of calculating the expected sales volume corresponding to the item group based on the expected sales volume corresponding to each of the plurality of items included in the item group; A step of calculating the actual sales volume corresponding to the item group based on the actual sales volume corresponding to each of the plurality of items; and A sales opportunity calculation method, comprising the step of calculating total error information corresponding to the item group based on the expected sales amount corresponding to the item group and the actual sales amount corresponding to the item group.

6. In paragraph 5, A sales opportunity calculation method, wherein the above total error information is calculated based on the weighted mean absolute percentage error (WMAPE) value between the actual sales quantity and the expected sales quantity corresponding to the item group.

7. In paragraph 5, In the above item group, a step of calculating total error information corresponding to all items except the first item among the plurality of items; A sales opportunity calculation method further comprising a step of calculating the error contribution of the first item based on the total error information corresponding to the entire remaining items and the total error information corresponding to the item group.

8. In paragraph 1, The steps to determine the above sales scenario are: A step of determining whether one or more scenario selection conditions corresponding to each of the one or more sales scenarios are satisfied based on at least some of the item information, timing information, sales-related information, out-of-stock information, and promotion information; and A method for calculating sales opportunities, comprising the step of determining at least one sales scenario corresponding to the item based on whether one or more of the above scenario selection conditions are satisfied.

9. In paragraph 8, For each of the above one or more sales scenarios, a priority is assigned to each scenario, A sales opportunity calculation method in which the satisfaction of the scenario selection conditions corresponding to each of the above sales scenarios is sequentially determined based on the priority of each scenario.

10. In paragraph 1, A step of calculating prediction bias information corresponding to the above item; and A sales opportunity calculation method further comprising a step of calculating a corrected expected sales amount corresponding to the item based on the expected sales amount and the predicted bias information.

11. In paragraph 10, A sales opportunity calculation method in which the above prediction bias information is calculated based on the error between the expected sales volume and the actual sales volume corresponding to the above item.

12. In paragraph 10, The above prediction bias information is, A sales opportunity estimation method, which is determined based on the sum of errors corresponding to overprediction and the sum of errors corresponding to underprediction among one or more error information corresponding to one or more dates.

13. In paragraph 10, The steps for calculating the above expected sales volume are: Including a step of calculating the above expected sales volume by date, The step of checking the above prediction bias information is: A step of calculating the actual sales volume corresponding to the item on a date basis corresponding to the above expected sales volume; and A sales opportunity calculation method further comprising a step of calculating forecast bias information corresponding to the item on a daily basis based on actual sales volume and expected sales volume corresponding to the item.

14. In electronic devices, One or more processors; comprising one or more memories storing instructions executed by the one or more processors; An electronic device, wherein when the instructions are executed by the one or more processors, the one or more processors are configured to execute the method according to any one of claims 1 to 13.

15. In a non-transitory computer-readable recording medium, instructions are recorded that cause one or more processors to perform an operation when executed by one or more processors. A non-transitory computer-readable recording medium configured to cause the one or more processors to execute a method according to any one of claims 1 to 13.

Images