Computer system and predictive model learning method

Abstract

To generate a model which can achieve an item demand prediction with a high degree of accuracy.SOLUTION: A computer system holds model information and actual result information. The model information includes information on a first model for predicting demand of a first item. The computer system: calculates a demand prediction of a second item in a first period, by using the first model; acquires a demand actual result of the second item in a second period having the same time width as the first period, from the actual result information; identifies a first analysis period within the first period and a second analysis period within the second period, in which an error of a shipping amount is large, on the basis of the demand prediction of the second item and the demand actual result of the second item; analyzes a generation period of a peak of the shipping amount of the first item in the first analysis period, and a generation period of a peak of the shipping amount of the second item in the second analysis period; and executes learning of a model including a feature amount defined on the basis of a result of the analysis.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a system and method for forecasting demand for an item. [Background technology]

[0002] To determine plans for labor, inventory, and replenishment in warehouses, a technology for predicting item demand using a predictive model is used. The features handled by the predictive model are determined when the predictive model is constructed.

[0003] As the items handled in a warehouse or the shipping patterns of the entire warehouse change over time, the features may no longer contribute to prediction. In addition, when applying an existing prediction model to a new warehouse or new items, it is necessary to adjust the features to suit the prediction target.

[0004] Adjusting the feature amount requires a lot of effort, which is a problem. To address this problem, a technique described in Patent Document 1 is known.

[0005] Patent Document 1 states that "the demand forecasting method for predicting future demand includes the steps of: calculating an error between a predicted value of past demand calculated by inputting actual measured values ​​of explanatory variables into a forecasting model constructed based on the actual measured values ​​of demand and explanatory variables, which are external factors that affect increases or decreases in demand; (S1) calculating an error between the predicted value of past demand and the actual measured values ​​of past demand; (S2) determining whether the calculated error is an abnormal value; (S3) acquiring new explanatory variables if it is determined that the error is an abnormal value; (S4) updating the forecasting model based on the acquired new explanatory variables; and (S5) predicting a new future demand using the updated forecasting model." [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 2017-016632 Summary of the Invention [Problem to be solved by the invention]

[0007] The technology described in Patent Document 1 acquires features input by a user or features of other existing models. In the case of user input, there is a problem that the cost is high. In the case of acquiring features of other models, the features are not necessarily those that contribute to the prediction of the prediction target.

[0008] The present invention provides a technique related to a method for adjusting feature quantities of a prediction model to improve prediction accuracy. [Means for solving the problem]

[0009] A representative example of the invention disclosed in the present application is as follows: A computer system including at least one computer, which holds model information for managing a model for predicting demand for an item and performance information for managing performance of demand for the item, and the model information includes: The feature values ​​calculated using input data including items related to the shipment of the first item are used as input, and information on a first model for forecasting demand for a first item, wherein the at least one computer: The feature values ​​calculated using input data including items related to the shipment of the second item in the first period are The first model By typing in , The aforementioned In the first period The aforementioned A demand forecast for a second item is calculated, and actual demand for the second item in a second period having the same time width as the first period is obtained from the actual demand information. A shipping volume is calculated based on the demand forecast for the second item and the actual demand for the second item. Forecast results and actual shipment volume a first analysis period within the first period and a second analysis period within the second period in which the error is large; an occurrence time of a peak in the shipping volume of the first item in the first analysis period and an occurrence time of a peak in the shipping volume of the second item in the second analysis period are analyzed; and based on the results of the analysis, change The features As input Run model training. [Effects of the Invention]

[0010] According to the present invention, it is possible to generate a model including features that contribute to improving prediction accuracy. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a demand forecasting system according to a first embodiment. [Figure 2] FIG. 2 is a diagram illustrating details of a functional unit of a computer according to a first embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of a data structure of shipping history management information according to the first embodiment. [Figure 4] FIG. 10 is a diagram illustrating an example of a data structure of analysis period information according to the first embodiment. [Figure 5] FIG. 4 is a diagram illustrating an example of a data structure of feature amount information according to the first embodiment. [Figure 6] 10 is a flowchart illustrating an outline of a process executed by a feature amount adjustment unit according to the first embodiment. [Figure 7A] 10 is a flowchart illustrating an example of a change pattern generation process executed by a feature amount adjustment unit according to the first embodiment. [Figure 7B] 10 is a flowchart illustrating an example of a change pattern generation process executed by a feature amount adjustment unit according to the first embodiment. [Figure 8] 10 is a flowchart illustrating an example of a verification process executed by a feature amount adjustment unit according to the first embodiment. [Figure 9A] FIG. 4 is a diagram showing an example of a screen displayed by a display unit according to the first embodiment. [Figure 9B] FIG. 4 is a diagram showing an example of a screen displayed by a display unit according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Examples of the present invention will be described below with reference to the drawings. However, the present invention should not be construed as being limited to the description of the following examples. Those skilled in the art will readily understand that the specific configuration can be modified without departing from the spirit or scope of the present invention. In the configurations of the invention described below, identical or similar components or functions are designated by the same reference numerals, and redundant description will be omitted. The designations "first," "second," "third," and the like in this specification are used to identify components and do not necessarily limit the number or order. The position, size, shape, and range of each component shown in the drawings may not represent the actual position, size, shape, and range, etc., in order to facilitate understanding of the invention. Therefore, the present invention is not limited to the position, size, shape, and range, etc., disclosed in the drawings, etc. [Example]

[0013] FIG. 1 is a diagram illustrating an example of a configuration of a demand forecasting system according to a first embodiment.

[0014] The demand forecasting system is a computer system configured with at least one computer 100. The computer 100 has a CPU 110, an IO interface 111, a network interface 112, a main memory device 113, and a secondary memory device 114. Each piece of hardware is connected to one another via a bus.

[0015] The CPU 110 executes a program stored in the main memory device 113. The CPU executes processing in accordance with the program, thereby operating as a functional unit (module) that realizes a specific function. In the following explanation, when processing is described using a functional unit as the subject, this indicates that the CPU is executing a program that realizes the functional unit.

[0016] The IO interface 111 is an interface for connecting to an external device. The computer 100 is connected to an input device 101 and an output device 102 via the IO interface 111. The input device 101 is a keyboard, a mouse, a touch panel, etc. The output device 102 is a display, a printer, etc.

[0017] The network interface 112 is an interface for connecting to an external device via the network 103. The network 103 is a wide area network (WAN), a local area network (LAN), etc. The connection format of the network 103 may be either wired or wireless.

[0018] The main memory device 113 stores programs executed by the CPU 110 and data used by the programs. The main memory device 113 also includes a work area temporarily used by the programs. The main memory device 113 is, for example, a dynamic random access memory (DRAM).

[0019] The main memory device 113 stores programs that implement the input unit 120, the prediction unit 121, the feature amount adjustment unit 122, and the display unit 123. The main memory device 113 also stores programs such as an OS (Operating System) that are not shown, but are omitted in this embodiment.

[0020] The input unit 120 accepts various inputs from a user via the input device 101 or the network 103. The prediction unit 121 predicts the demand for an item during a prediction period and outputs the prediction results. The prediction period is a time range for predicting the demand for an item, such as a year, a month, or a week. Note that the prediction period is not limited to these. The prediction period is assumed to be set in advance. The feature adjustment unit 122 adjusts the features of an existing prediction model when the prediction accuracy of the existing prediction model deteriorates or when an existing prediction model is used to generate a prediction model to be applied to a new prediction target. The display unit 123 presents the prediction results and information related to the features to the user via the output device 102. Note that the computer 100 may accept inputs from a user by receiving data from a user terminal communicatively connected via the network 103, and output data to the user terminal by transmitting output to be output by the output device 102 to the user terminal.

[0021] The secondary storage device 114 permanently stores data and is, for example, a hard disk drive (HDD) or a solid state drive (SSD).

[0022] The secondary storage device 114 stores shipping history management information 130, input data management information 131, and prediction model management information 132. The secondary storage device 114 also stores information (not shown) such as information for managing item characteristics, but this information is omitted in this embodiment.

[0023] The shipping history management information 130 stores data (shipping history) related to past shipments of items. The shipping history includes the amount of items shipped during a measurement period. The measurement period may be, for example, a day, a week, or a month. However, the measurement period is not limited to these. The data structure of the shipping history management information 130 will be described with reference to FIG. 2.

[0024] The input data management information 131 stores input data to be input to the forecasting model. The input data includes values ​​for items such as the item type, the amount of the item in stock, the amount of the item shipped, and whether or not there is a sale. The input data may be input directly to the forecasting model, or pre-processed input data may be input. The shipping history itself may also be treated as input data. In this case, the input data management information 131 can be considered the same as the shipping history management information 130.

[0025] The prediction model management information 132 stores definition information of a mathematical model (prediction model) that predicts the demand for an item. The prediction model management information 132 stores information on feature quantities, item characteristics such as item type and category, and model definition information according to warehouse characteristics. The prediction model is, for example, a decision tree or a neural network. Note that the present invention is not limited to the type and structure of the prediction model.

[0026] The demand forecasting system may be configured with multiple computers 100. In this case, functional units are distributed among the multiple computers 100. For example, the input unit 120 is disposed in one computer 100, the prediction unit 121 is disposed in another computer 100, the feature adjustment unit 122 is disposed in another computer 100, and the display unit 123 is disposed in another computer 100.

[0027] The programs and data stored in the main memory device 113 may be stored in the secondary memory device 114. In this case, the CPU 110 reads the programs and data from the secondary memory device 114 and stores them in the main memory device 113.

[0028] FIG. 2 is a diagram illustrating the details of the functional units of the computer 100 according to the first embodiment.

[0029] The input unit 120 inputs input data information 211 including input data for a first period of a second item to the prediction unit 121, inputs shipping history information 212 including the shipping history of the second item for a second period to the feature amount adjustment unit 122, and inputs a prediction model 213 for the first item to the prediction unit 121 and the feature amount adjustment unit 122. Note that the measurement period of the input data information 211 is the same as the measurement period of the shipping history information 212. Also, the time span of the first period is the same as the time span of the second period. The time span of the first period is, for example, one year.

[0030] Here, the combination of item and period is one of the following: (Pattern 1) The first item and the second item are the same, but the first period and the second period are different. (Pattern 2) The first period and second period are the same, but the first item and second item are different. (Pattern 3) The first item and the second item are different, and the first period and the second period are different.

[0031] Pattern 1 is intended for situations where features need to be adjusted due to a decline in the predictive accuracy of an existing model. Patterns 2 and 3 are intended for situations where a predictive model for a new item needs to be generated.

[0032] The prediction unit 121 acquires the prediction model 213 for the first item, inputs the input data information 211 to the prediction model 213 to generate predicted shipment quantity information 214, and outputs it to the feature amount adjustment unit 122.

[0033] The analysis period identification unit 201 of the feature amount adjustment unit 122 extracts an analysis period based on the shipping history information 212 and the predicted shipping amount information 214, and generates analysis period information 215. The analysis period is a period shorter than the measurement period, and is a period during which analysis related to the feature amount is performed.

[0034] The change pattern generation unit 202 generates a change pattern of feature quantities from the existing model based on the difference between the two shipping patterns in the analysis period, and outputs it as a change pattern list 216.

[0035] The verification unit 203 changes the features of the prediction model 213 based on the prediction model 213 and the change pattern list 216, and executes learning of the prediction model 213. The verification unit 203 also causes the prediction unit 121 to execute prediction using the updated prediction model 213. The verification unit 203 identifies features that contribute to improving prediction accuracy based on the shipment volume prediction result, and selects features to be used in a new prediction model. The verification unit 203 outputs the processing result to the display unit 123 as feature information 217.

[0036] The display unit 123 displays information related to the feature amount based on the feature amount information 217 output from the feature amount adjustment unit 122 .

[0037] It should be noted that, with regard to each functional unit included in the computer 100, multiple functional units may be combined into one functional unit, or one functional unit may be divided into multiple functional units for each function. For example, the change pattern generation unit 202 may include an analysis period identification unit 201.

[0038] The input unit 120 may input, instead of the input data information 211, shipping history information of the second item that has a small error from the prediction using the prediction model 213 to the feature amount adjustment unit 122. In this case, the analysis period identification unit 201 extracts the analysis period based on the two shipping histories.

[0039] FIG. 3 is a diagram illustrating an example of the data structure of the shipping history management information 130 according to the first embodiment.

[0040] The shipping history management information 130 stores the shipping history of multiple items. Specifically, the shipping history management information 130 stores entries including an item ID 301, a shipping date 302, and a shipping quantity 303. One entry corresponds to one shipping history. The shipping history management information 130 shown in FIG. 3 stores shipping history for a measurement period of one day.

[0041] Item ID 301 is a field that stores identification information of an item. Shipping date 302 is a field that stores the shipping date of the item. Shipping volume 303 is a field that stores the shipping volume of the item per day.

[0042] FIG. 4 is a diagram illustrating an example of the data structure of the analysis period information 215 according to the first embodiment.

[0043] The analysis period information 215 stores entries each including a period ID 401, an analysis period 402, and a difference pattern 403. One entry corresponds to one analysis period.

[0044] Period ID 401 is a field that stores identification information for the analysis period. Analysis period 402 is a field that stores the analysis period. Difference pattern 403 is a field that stores a value that indicates the pattern of differences between the time series of two shipments. Either "1st" or "2nd" is stored in difference pattern 403. "1st" indicates that there is a characteristic peak in the time series of the shipment forecast for the second item. "2nd" indicates that there is a characteristic peak in the time series of the shipping history for the second item.

[0045] In the following description, an analysis period in which the difference pattern 403 is "first" will be referred to as a first type analysis period, and an analysis period in which the difference pattern 403 is "second" will be referred to as a second type analysis period.

[0046] FIG. 5 is a diagram illustrating an example of the data structure of the feature amount information 217 according to the first embodiment.

[0047] The feature amount information 217 stores entries each including a feature amount name 501, a feature amount description 502, a corresponding feature amount name 503, and a new flag 504. One entry corresponds to one feature amount.

[0048] Feature name 501 is a field for storing the name of the feature. Feature description 502 is a field for storing an explanation of the feature, such as the meaning of the feature and the values ​​that the feature can take. Corresponding feature name 503 is a field for storing the name of the feature used when generating the feature. New flag 504 is a field for storing a flag indicating whether the feature is newly generated. New flag 504 stores either "1" indicating a newly generated feature or "0" indicating an existing feature.

[0049] FIG. 6 is a flowchart illustrating an outline of the process executed by the feature amount adjustment unit 122 according to the first embodiment.

[0050] The feature amount adjustment unit 122 acquires the predicted shipping quantity information 214 of the second item and the shipping history information 212 of the second item (Step S101).

[0051] Next, the analysis period specifying unit 201 of the feature amount adjusting unit 122 specifies an analysis period based on the predicted shipping amount information 214 and the shipping history information 212, and generates analysis period information 215 (step S102). Specifically, the following process is executed.

[0052] (S102-1) The analysis period specifying unit 201 sets the start date and time of the first period in the forecast shipment quantity information 214 to a variable t1, and sets the start date and time of the second period in the shipment history information 212 to a variable t2.

[0053] (S102-2) The analysis period identification unit 201 acquires a time series of shipment forecasts for the processing time range from variable t1 from the forecast shipment quantity information 214, and acquires a time series of shipment history for the processing time range from variable t2 from the shipping history information 212. Here, the processing time range is a period shorter than the first period and can be set arbitrarily. The processing time range is, for example, one month.

[0054] (S102-3) The analysis period specifying unit 201 calculates the absolute value of the error in the shipment amount for each measurement period within the processing time range, and also calculates the sum of the absolute values ​​of the errors.

[0055] (S102-4) The analysis period identification unit 201 determines whether the sum of the absolute values ​​of the errors is greater than a first threshold and whether the maximum absolute value of the errors in the shipment volume during the measurement period is greater than a second threshold. The first threshold and the second threshold can be set arbitrarily. For example, the first threshold can be set to twice the average error.

[0056] (S102-5) If the above conditions are met, the analysis period identification unit 201 registers the time range as an analysis period in the analysis period information 215. The value of the difference pattern 403 is set based on the error. That is, if there is a peak in the time series of the shipping history, the difference pattern 403 is "second," and if there is a peak in the time series of the shipping forecast, the difference pattern 403 is "first."

[0057] (S102-6) The analysis period identification unit 201 adds the processing time range to the variables t1 and t2.

[0058] (S102-7) The analytical period identification unit 201 determines whether the variable t1 has not passed the end time of the first period and whether the variable t2 has not passed the end time of the second period. If the above conditions are not met, the analytical period identification unit 201 returns to S102-2 and executes the same processing. If the above conditions are not met, the analytical period identification unit 201 ends the processing of step S102.

[0059] As described above, in this embodiment, a period in which the error is large and a characteristic peak exists in either the time series of the shipping history or the time series of the shipping forecast of the second item is extracted as the analysis period.

[0060] Next, the change pattern generation unit 202 of the feature amount adjustment unit 122 executes a change pattern generation process (step S103). Details of the change pattern generation process will be described with reference to Figs. 7A and 7B.

[0061] Next, the verification unit 203 of the feature amount adjustment unit 122 executes a verification process (step S104), and outputs the feature amount information 217 to the display unit 123 (step S105). Details of the verification process will be described with reference to FIG.

[0062] 7A and 7B are flowcharts illustrating an example of a change pattern generation process executed by the feature amount adjustment unit 122 according to the first embodiment.

[0063] The change pattern generation unit 202 refers to the analysis period information 215 and determines whether or not only the first type analysis period exists (step S201).

[0064] If only the first type analysis period exists, the change pattern generation unit 202 starts loop processing of the first type analysis period (step S202). Specifically, the change pattern generation unit 202 selects one first type analysis period.

[0065] The change pattern generation unit 202 generates additional candidate features based on the time series of shipment forecasts for the selected first type analysis period of the forecast shipment volume information 214 (step S203).

[0066] Specifically, the change pattern generation unit 202 generates a feature related to the date and time when the shipment volume is at its maximum (peak date and time) as an additional candidate feature. The feature is, for example, a flag indicating a sale day, and is set to "1" if the current date and time is a sale day and "0" if the current date and time is not a sale day.

[0067] The change pattern generation unit 202 determines whether or not the processing has been completed for all first type analysis periods (step S204).

[0068] If the processing has not been completed for all of the first type analysis periods, the change pattern generation unit 202 returns to step S202 and executes the same processing.

[0069] When the processing for all first type analysis periods is completed, the change pattern generation unit 202 generates a change pattern (step S205). The change pattern is composed of identification information and identification information of one or more feature amounts. The change pattern generation unit 202 registers the generated change pattern in the change pattern list 216.

[0070] Specifically, the change pattern generation unit 202 generates a change pattern including an existing feature and one or more candidate features to be added. If there are multiple candidate features to be added, two or more change patterns are generated. Note that an upper limit may be set on the number of change patterns to be generated. Note that the change pattern includes the existing feature as is.

[0071] If it is determined in step S201 that an analysis period other than the first type analysis period is included, the change pattern generation unit 202 determines whether or not only the second type analysis period exists (step S206).

[0072] If only the second type analysis period exists, the change pattern generation unit 202 starts loop processing of the second type analysis period (step S207). Specifically, the change pattern generation unit 202 selects one second type analysis period.

[0073] The change pattern generation unit 202 identifies deletion candidate features based on the time series of the shipping history of the selected second type analysis period of the shipping history information 212 (step S208).

[0074] Specifically, the change pattern generation unit 202 identifies, as deletion candidate feature quantities, feature quantities related to the date and time when the shipping volume is at its maximum (peak date and time).

[0075] The change pattern generation unit 202 determines whether or not the processing has been completed for all second type analysis periods (step S209).

[0076] If the processing has not been completed for all second type analysis periods, the change pattern generation unit 202 returns to step S207 and executes the same processing.

[0077] When the processing is completed for all the second type analysis periods, the change pattern generation unit 202 generates a change pattern (step S210). The change pattern generation unit 202 registers the generated change pattern in the change pattern list 216.

[0078] Specifically, the change pattern generation unit 202 generates a change pattern by deleting one or more deletion candidate features from existing features. If there are multiple deletion candidate features, two or more change patterns are generated. Note that an upper limit may be set on the number of change patterns to be generated. Note that the change pattern includes existing features other than the deletion candidate features as they are.

[0079] If it is determined in step S206 that the first type analysis period and the second type analysis period are included, the change pattern generation unit 202 generates a period pair by combining the first type analysis period and the second type analysis period (step S211).

[0080] The change pattern generation unit 202 starts a loop process of the period pair (step S212). Specifically, the change pattern generation unit 202 selects one period pair.

[0081] The change pattern generation unit 202 generates candidate features to be added and identifies candidate features to be deleted (step S213). The method for generating candidate features to be added is the same as that in step S203, and the method for identifying candidate features to be deleted is the same as that in step S208. In generating candidate features to be added, the change pattern generation unit 202 may generate candidate features to be added based on candidate features to be deleted. For example, if the feature related to the first day of the second type analysis period is a candidate feature to be deleted, the change pattern generation unit 202 generates the feature related to the first day of the first type analysis period as a candidate feature to be added.

[0082] The change pattern generation unit 202 determines whether or not the process has been completed for all period pairs (step S214).

[0083] If the process has not been completed for all period pairs, the change pattern generation unit 202 returns to step S212 and executes the same process.

[0084] When the process has been completed for all period pairs, the change pattern generation unit 202 generates a change pattern (step S215). The change pattern generation unit 202 registers the generated change pattern in the change pattern list 216.

[0085] Specifically, the change pattern generation unit 202 generates a change pattern by adding one or more feature quantities candidate for addition and deleting one or more feature quantities candidate for deletion from existing feature quantities. Note that an upper limit may be set on the number of change patterns to be generated. Note that the change pattern includes existing feature quantities other than the feature quantities candidate for deletion as they are.

[0086] FIG. 8 is a flowchart illustrating an example of a verification process executed by the feature amount adjustment unit 122 according to the first embodiment.

[0087] The verification unit 203 acquires the prediction model 213 and the change pattern list 216 (step S301), and also acquires the input data information 211 and shipping history information of the second item (step S302). The shipping history information of the second item is treated as correct data for prediction.

[0088] The verification unit 203 starts a loop process of the change patterns (step S303). Specifically, the verification unit 203 selects one change pattern.

[0089] The verification unit 203 sets features based on the change pattern and executes a learning process for the prediction model 213 (step S304). As a result, a new prediction model is generated from the existing prediction model 213. Note that a well-known learning method may be used, and therefore detailed description thereof will be omitted.

[0090] The verification unit 203 inputs the new prediction model and input data information 211 to the prediction unit 121 and instructs the prediction unit 121 to execute prediction (step S305). The verification unit 203 acquires the predicted shipment amount information 214 from the prediction unit 121.

[0091] The verification unit 203 calculates an evaluation index for the new prediction model based on the shipping history information and the forecast shipping quantity information 214 of the second item (step S306). For example, the verification unit 203 calculates the mean square error between the shipping performance and the shipping forecast.

[0092] The verification unit 203 determines whether or not the process has been completed for all change patterns (step S307).

[0093] If the processing has not been completed for all change patterns, the verification unit 203 returns to step S303 and executes the same processing.

[0094] When the processing for all change patterns is completed, the verification unit 203 selects a feature based on the evaluation index (step S308). For example, the verification unit 203 may select a feature based on the change pattern that most improves the prediction accuracy, or the verification unit 203 may select a feature by combining multiple change patterns that improve the prediction accuracy.

[0095] 9A and 9B are diagrams showing examples of screens displayed by the display unit 123 according to the first embodiment.

[0096] The display unit 123 generates display information for displaying the screen 900 based on the feature amount information 217 .

[0097] The feature amount information 217 is displayed on the screen 900. When the user double-clicks on a candidate feature amount to be added, the display unit 123 displays a screen 910 as shown in Fig. 9B.

[0098] A graph showing a shipping forecast for an item is displayed on screen 910. Symbols indicating the dates and times corresponding to candidate features to be added and symbols indicating the dates and times corresponding to existing features used to generate candidate features to be added are superimposed on the graph.

[0099] The change patterns and evaluation indices may be displayed on the screen 900 so that the user can select a feature amount.

[0100] According to the present invention, the feature amount adjustment unit 122 can select feature amounts that contribute to improving the prediction accuracy of the shipment amount of an item in an arbitrary period, and generate a prediction model with high prediction accuracy.

[0101] The present invention is not limited to the above-described embodiments, but includes various modifications. For example, the above-described embodiments are provided to explain the present invention in detail, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, some of the configurations of each embodiment can be added to, deleted from, or replaced with other configurations.

[0102] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that implements the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for providing such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, solid-state drives (SSDs), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, and ROMs.

[0103] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, Python, and Java (registered trademark).

[0104] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read and execute the program code stored in the storage means or storage medium.

[0105] In the above-described embodiment, the control lines and information lines are those that are considered necessary for the explanation, and not all control lines and information lines are necessarily shown in the product. All components may be interconnected. [Explanation of symbols]

[0106] 100 calculator 101 Input Device 102 Output Device 103 Network 110 CPU 111 IO interface 112 Network Interface 113 Main storage 114 Secondary storage device 120 Input section 121 Prediction Department 122 Feature Adjustment Unit 123 Display section 130 Shipping history management information 131 Input data management information 132 Prediction Model Management Information 201 Analysis period identification section 202 Change pattern generation unit 203 Verification Department 211 Input Data Information 212 Shipping History Information 213 Predictive Model 214 Forecast shipping volume information 215 Analysis period information 216 Change Pattern List 217 Feature Information 900, 910 screen

Claims

1. A computer system comprising at least one computer, The system holds model information for managing a model for predicting the demand for an item and actual result information for managing the actual demand for the item, the model information includes information about a first model that uses, as input, feature quantities calculated using input data including items related to shipment of a first item and predicts the demand for the first item; The at least one computer calculating a demand forecast for the second item in the first period by inputting into the first model a feature calculated using input data including items related to shipment of the second item in the first period; From the performance information, a demand performance of the second item during a second period having the same time width as the first period is obtained; identifying a first analysis period within the first period and a second analysis period within the second period in which an error between the predicted shipping amount and the actual shipping amount is large based on the demand forecast for the second item and the actual demand for the second item; Analyzing a peak occurrence time of the shipping amount of the first item in the first analysis period and a peak occurrence time of the shipping amount of the second item in the second analysis period; A computer system characterized in that model learning is performed using, as input, feature quantities that have been changed based on the results of the analysis.

2. 2. The computer system of claim 1, The at least one computer Calculating an error between the demand forecast and the actual demand for the second item for each unit time interval along the time series; identifying a partial period of the first period in which the error is greater than a threshold and a peak in the shipping volume of the second item exists as the first analysis period; a partial period of the second period in which the error is greater than a threshold value and in which a peak in the shipment volume of the second item occurs is identified as the second analysis period.

3. 3. The computer system according to claim 2, The at least one computer identifying, based on the first model, a feature associated with a time when a peak in the shipment volume of the first item occurs during the first analysis period as a deletion candidate feature; generating, as an additional candidate feature, a feature associated with a time when a peak in the shipment volume of the second item occurs during the second analysis period based on the actual demand for the second item; generating a feature change pattern based on the deletion candidate feature and the addition candidate feature; A computer system that learns a model using, as an input, feature amounts changed based on the feature amount change pattern.

4. 4. The computer system according to claim 3, The at least one computer generating a pair of the first analysis period and the second analysis period; A computer system comprising: a computer that generates the additional candidate feature based on a feature associated with a time when a peak in shipping volume of the first item occurs during the first analysis period.

5. 4. The computer system according to claim 3, The at least one computer Evaluating the predictive accuracy of the model generated by the learning; Selecting the feature quantity to be handled by the model based on the result of the evaluation; A computer system that presents the selected feature quantities.

6. A method for training a predictive model executed by a computer system having at least one computer, comprising: the computer system holds model information for managing a model for predicting demand for an item, and performance information for managing actual demand performance for the item; the model information includes information about a first model that uses, as input, feature quantities calculated using input data including items related to shipment of a first item and predicts the demand for the first item; a first step in which the at least one computer calculates a demand forecast for the second item in the first time period by inputting, into the first model, feature quantities calculated using input data including items related to shipment of the second item in the first time period; a second step in which the at least one computer acquires, from the performance information, actual demand data for the second item during a second period having the same time duration as the first period; a third step in which the at least one computer identifies a first analysis period within the first period and a second analysis period within the second period in which there is a large error between the shipping volume prediction result and the shipping volume actual result, based on the demand forecast for the second item and the demand actual result for the second item; a fourth step in which the at least one computer analyzes a peak occurrence time of the shipping amount of the first item in the first analysis period and a peak occurrence time of the shipping amount of the second item in the second analysis period; a fifth step in which the at least one computer executes model training using the feature values ​​modified based on the results of the analysis as input.

7. The prediction model learning method according to claim 6, The third step includes: a step of calculating an error between the demand forecast and actual demand for the second item for each unit time interval along a time series by the at least one computer; the at least one computer identifying, as the first analysis period, a partial period of the first period in which the error is greater than a threshold and in which a peak in the shipping volume of the second item occurs; and the at least one computer specifies as the second analysis period a partial period of the second period in which the error is greater than a threshold and in which a peak in the shipment volume of the second item occurs.

8. The prediction model learning method according to claim 7, The fourth step includes: a sixth step in which the at least one computer identifies, based on the first model, a feature associated with a time when a peak in the shipment volume of the first item occurs in the first analysis period, as a deletion candidate feature; a seventh step in which the at least one computer generates, as additional candidate features, feature quantities related to the timing of occurrence of peaks in the shipment volume of the second item in the second analysis period, based on the actual demand for the second item; an eighth step of generating, by the at least one computer, a feature change pattern based on the deletion candidate feature and the addition candidate feature; The fifth step is a method for training a prediction model, characterized in that it includes a step in which the at least one computer trains a model using, as input, features modified based on the feature modification pattern.

9. The prediction model learning method according to claim 8, The seventh step includes: generating a pair of the first analysis period and the second analysis period by the at least one computer; and generating the additional candidate features based on features related to the timing of a peak in the shipment volume of the first item during the first analysis period.

10. The prediction model learning method according to claim 8, a step of evaluating, by the at least one computer, the predictive accuracy of the model generated by the training; selecting, by the at least one computer, the feature quantities to be handled by the model based on the results of the evaluation; and a step in which the at least one computer presents the selected feature quantities.

Images