Information processing apparatus

Abstract

A calculation unit 14 of an information processing apparatus 10 uses a hierarchical Bayesian model in which stores that have implemented a plurality of past campaigns and the business categories of the stores are included in different hierarchical levels, and new campaign information which is acquired, to calculate effect information relating to the effect of a new campaign. In the hierarchical Bayesian model, when yi is an estimated value of the causal effect of each of the campaigns, θi is the mean, and σi 2 is the variance, yi ~ N(θi,σi 2), and when zai is a j-dimensional store dummy variable, zbi is an i-dimensional business category dummy variable, xi is another explanatory variable, α is an intercept, θa is a store effect, θb is a business category effect, and β is the coefficient for xi, θi = α + θa Tzai + θb Tzbi + βTxi, θaj ~ (0,τa 2), where j = 1, …, J, and θbk ~ (0,τb 2), where k = 1, …, K.

Description

Information processing device

[0001] The present invention relates to a technique for predicting the effectiveness of a campaign conducted in a store or the like.

[0002] Various measures (hereinafter referred to as campaigns) are being implemented for the purpose of sales promotion. For example, Patent Literature 1 discloses a method for distinguishing between a customer group that purchased a target product during a campaign period and a customer group that did not, and calculating the effectiveness of the campaign from the difference in sales increase rate during the promotion period for these identified customer groups.

[0003] JP 2013-57990 A

[0004] In view of the above-mentioned background, an object of the present invention is to predict the effectiveness of a new campaign by utilizing knowledge gained from past campaigns.

[0005] In order to solve the above problem, the present invention provides an information processing device characterized by comprising: an acquisition unit that acquires new campaign information including information on stores that will be implementing a new campaign that is scheduled to be implemented and the business type to which each of the stores belongs; a hierarchical Bayesian model that includes stores that have implemented multiple campaigns in the past and the business type to which each of the stores belongs, each at a different hierarchical level; a calculation unit that uses the acquired new campaign information to calculate effectiveness information regarding the effectiveness of the new campaign; and an output unit that outputs the calculated effectiveness information.

[0006] The present invention also provides an information processing method characterized by comprising an acquisition step of acquiring new campaign information including information on stores that will be implementing a new campaign that is scheduled to be implemented and the business type to which each of the stores belongs; a hierarchical Bayes model that includes stores that have implemented multiple campaigns in the past and the business type to which each of the stores belongs, each at a different hierarchical level; a calculation step of calculating effectiveness information regarding the effectiveness of the new campaign using the acquired new campaign information; and an output step of outputting the calculated effectiveness information.

[0007] According to the present invention, it is possible to estimate the effectiveness of a new campaign by utilizing knowledge gained from past campaigns.

[0008] 1 is a block diagram showing an example of the hardware configuration of an information processing device 10 according to an embodiment of the present invention; FIG. 2 is a block diagram showing an example of the functional configuration of the information processing device 10; FIG. 3 is a diagram explaining an overview of a hierarchical Bayes model in this embodiment; FIG. 4 is a flowchart showing an example of the operation of the information processing device 10; FIG. 5 is a diagram illustrating a horseshoe prior; and FIG. 6 is a table explaining the effect of this embodiment, showing evaluation results of the estimation accuracy of each model.

[0009] [Embodiment] [Configuration] FIG. 1 is a diagram showing the hardware configuration of an information processing device 10 according to an embodiment of the present invention. The information processing device 10 is physically configured as a computer including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, and a bus connecting these devices. Each of these devices operates using power supplied from a battery (not shown). In the following description, the term "device" may be interpreted as a circuit, device, unit, or the like. The hardware configuration of the information processing device 10 may be configured to include one or more of the devices shown in FIG. 1, or may be configured without including some of the devices. Furthermore, the information processing device 10 may be configured by communicating with multiple devices each having a different housing.

[0010] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0011] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. Furthermore, for example, a baseband signal processing unit, a call processing unit, etc. may be realized by the processor 1001.

[0012] The processor 1001 reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described below. The functional blocks of the information processing device 10 may be implemented by a control program stored in the memory 1002 and running on the processor 1001. Various processes may be executed by one processor 1001, or may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted to the information processing device 10 via a telecommunications line.

[0013] The memory 1002 is a computer-readable recording medium and may be configured by at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing the method according to this embodiment.

[0014] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device.

[0015] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0016] Each device, such as the processor 1001 and the memory 1002, is connected by a bus for communicating information. The bus may be configured using a single bus, or may be configured using different buses between each device.

[0017] The information processing device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0018] 2 is a block diagram showing the functional configuration of the information processing device 10. In the information processing device 10, a processor 1001 reads a program or the like from a storage 1003 to a memory 1002 and executes the program, thereby realizing the functions of an acquisition unit 11, a storage unit 12, a generation unit 13, a calculation unit 14, and an output unit 15.

[0019] The acquisition unit 11 acquires information from an external source. For example, the acquisition unit 11 acquires past campaign information, which is information about multiple campaigns conducted in the past. The past campaign information includes, for example, information about stores that conducted each past campaign and the business type to which the store belongs, and information about the effectiveness of each campaign. The information about the stores that conducted each past campaign is, for example, the name of the store (or the name of the franchise chain if the store is a franchise chain store). The information about the business type to which the stores that conducted each past campaign belong is a classification category based on the business format of the store in the retail or restaurant industry. For example, in the retail industry, it may be a supermarket, convenience store, department store, fast food restaurant, drugstore, electronics retailer, fashion store, discount store, etc. Note that, in this embodiment, the term "store" may include, in addition to a store existing in a real three-dimensional space, an online shop, etc. on the Internet. The information about the effectiveness of each campaign is information indicating the effectiveness before and after each campaign, such as sales and profits obtained by the campaign, customer satisfaction, etc. Information indicating these effects can be obtained by the person who conducted the campaign calculating the difference in sales or profits before and after the campaign, or by analyzing changes in customer satisfaction based on surveys or the like.

[0020] The acquisition unit 11 also acquires new campaign information, which is information about a new campaign that is scheduled to be newly implemented. The new campaign information includes, for example, information about the store that will be implementing the new campaign and the business type to which each store belongs. The information about the store that will be implementing the new campaign is, for example, the name of the store (or the name of the franchise chain if the store is a franchise chain store). The information about the business type to which the store that will be implementing the new campaign belongs is a classification item based on differences in business formats in the retail industry or the restaurant industry, such as supermarkets, convenience stores, department stores, fast food stores, drug stores, electronics retailers, fashion stores, discount stores, etc. in the retail industry.

[0021] The information acquired by the acquisition unit 11 as described above is stored in the storage unit 12 .

[0022] The generation unit 13 generates a hierarchical Bayesian model using the past campaign information acquired by the acquisition unit 11, i.e., information about stores that have implemented multiple past campaigns and the business types to which those stores belong, as well as information about the effectiveness of each campaign. The hierarchical Bayesian model is a hierarchical statistical model described in multiple different layers. The hierarchical Bayesian model is based on a Bayesian model that quantifies post-hoc analysis with uncertainty, and takes into account trends in individual data and trends in overall data among data with different characteristics. As shown in FIG. 3 , the hierarchical Bayesian model of this embodiment has a hierarchical structure with multiple layers for the entire store group, where the top layer is the "business type" to which the store belongs, the next layer is the "store" that implemented the campaign, and the bottom layer is the "campaign" that was held.

[0023] The details of the hierarchical Bayes model according to this embodiment are as follows: i Let be the estimate of the causal effect of each campaign, and θ i is the mean, and σ i 2 When y is the variance, i ~N(θ i , σ i 2) In other words, each observation in the hierarchical Bayes model (the estimated value y i ) is the average θ i and variance σ i 2 (i.e., the standard error of the estimated causal effect) follows a normal distribution. Note that the estimated causal effect of the campaign, y i is information about the effectiveness of each past campaign acquired by the acquisition unit 11.

[0024] And z ai is the j-dimensional store dummy variable, z bi is the i-dimensional business type dummy variable, x i is another explanatory variable (for example, the period during which the campaign is running), α is the intercept, and θ a is the store effect, θ b is the business type effect, β is x i The coefficient of τ a is its variance, τ b When θ is the variance, i = α + θ a T z ai +θ b T z bi +β T x i θ aj ~(0,τ a 2 ),j=1,…,J θ bk ~(0,τ b 2 ), k=1,…,K. This formula divides the effect of each campaign into fixed effects (α, β) that are common to these campaigns and variable effects (θ a , θ b ) is formulated as a mixed model that combines

[0025] In the above formula, T means the transpose matrix. aj , θ bk are independent normal distributions, and are generated and updated independently in the generation (i.e., learning) of the hierarchical Bayesian model. a , θ bare assumed to be independent, i.e., do not affect each other. Store dummy variable z ai is prepared for the number j of stores, and takes the value "1" if it applies and "0" if it does not. For example, if the store name is "Franchise Chain XXX", the dummy variable z for stores that belong to franchise chain XXX is ai is "1", and the store dummy variable z for stores other than franchise chain XXX ai are all "0". The store dummy variable z ai If there are multiple stores, z is used for each of these stores. ai = 1. Similarly, the business type dummy variable z bi There are as many variables as there are business types i, and they take the value "1" if they apply and "0" if they do not. For example, when the business type is "convenience store," the business type dummy variable z bi is "1", and the business type dummy variable z bi are all "0". The business type dummy variable z bi If there are multiple applicable business types, z is used for each of these multiple business types. bi =1.

[0026] By the hierarchical Bayesian model expressed by the above formula, τ a , τ b , θ i can be estimated.

[0027] In addition, the store dummy variable z ai and business type dummy variable z bi When the number of campaigns per store and business type is not so large, it is assumed that the number of data is insufficient for the required accuracy, i.e., the data is sparse. a and business type effect θ b The prior distribution of may be a horseshoe prior as shown in FIG. 4. This makes it possible to deal with sparsity when the number of campaigns per store and business type is not so large. The hierarchical Bayes model generated by the generation unit 13 is stored in the storage unit 12.

[0028] 2 , the calculation unit 14 calculates effect information regarding the effect of the new campaign using the new campaign information acquired by the acquisition unit 11, i.e., information regarding the stores implementing the new campaign and the business type to which each of the stores belongs, and the hierarchical Bayes model stored in the storage unit 12. Specifically, the calculation unit 14 calculates the effect information of the new campaign by inputting the new campaign information into the hierarchical Bayes model. This effect information is expressed in the same format as the information regarding the effect of the campaign used when generating the hierarchical Bayes model, and includes, for example, sales, profits, customer satisfaction, etc., obtained through the new campaign.

[0029] The output unit 15 outputs the effect information calculated by the calculation unit 14 to the outside. The output here includes all output forms such as transmission, display, writing to a storage medium, and printing.

[0030] [Operation] Next, the operation of this embodiment will be described. Fig. 5 is a flowchart showing an example of the operation of the information processing device 10. Before the process shown in Fig. 5 is started, it is assumed that the hierarchical Bayesian model generated by the generation unit 13 is stored in the storage unit 12.

[0031] The acquisition unit 11 acquires new campaign information input to the information processing device 10 via a communication network (not shown) (step S11). The new campaign information acquired by the acquisition unit 11 is stored in the storage unit 12.

[0032] The calculation unit 14 calculates effectiveness information regarding the effectiveness of the new campaign using the new campaign information acquired by the acquisition unit 11 and stored in the memory unit 12 and the hierarchical Bayes model stored in the memory unit 12 (step S12).

[0033] The output unit 15 outputs the effect information calculated by the calculation unit 14 to the outside (step S13).

[0034] Next, the effects of the above embodiment will be described with reference to Figures 6 and 7. The inventors have confirmed that the estimation accuracy of the method using the hierarchical Bayesian model according to this embodiment is better than that of commonly used methods for estimating causal effects. Specifically, in addition to models A, B, and C that are commonly used for estimating causal effects, the store effect θ a and business type effect θ b The hierarchical Bayes model does not use the horseshoe prior as a prior distribution of θ a and business type effect θ b The estimation accuracy of each model was evaluated using the horseshoe prior as the prior distribution of the hierarchical Bayes model, and the RMSE (Root Mean Squared Error) was used as the evaluation value. The smaller the RMSE value, the smaller the model's error.

[0035] Figure 6 is a table showing the evaluation results of the estimation accuracy of each model. As shown in Figure 6, the store effect θ a and business type effect θ b It was confirmed that the RMSE of the hierarchical Bayes model using the horseshoe prior as the prior distribution of is the smallest, and that it is the model with the smallest error. a and business type effect θ b The RMSE of the hierarchical Bayes model that does not use the horseshoe prior as the prior distribution is also sufficiently small compared to, for example, models A and B, and it was confirmed that the model has a relatively small error.

[0036] According to the above embodiment, it is possible to predict with sufficient accuracy the effectiveness of a new campaign by utilizing knowledge of past campaigns.

[0037] [Modifications] The present invention is not limited to the above-described embodiment. The above-described embodiment may be modified as follows. Furthermore, two or more of the following modifications may be combined and implemented.

[0038] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0039] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0040] For example, the information processing device 10 according to an embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure.

[0041] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (New Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA1000, UMB (ULtra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (ULtra-WIDE Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems extended based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G, etc.) may also be applied.

[0042] The present invention may also be an information processing method comprising: an acquisition step of acquiring campaign information including information on stores that will be running a new campaign and the business types to which each of the stores belongs; a hierarchical Bayesian model including stores that have run multiple campaigns in the past and the business types to which the stores belong, each at a different hierarchical level; a calculation step of calculating effectiveness information regarding the effectiveness of the new campaign using the acquired campaign information; and an output step of outputting the calculated effectiveness information. The processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be reordered as long as they are consistent. For example, the methods described in this disclosure present various step elements in an exemplary order and are not limited to the specific order presented.

[0043] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0044] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0045] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0046] Software, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise, should be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc. Additionally, software, instructions, information, etc. may be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then such wired and / or wireless technologies are included within the definition of a transmission medium.

[0047] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

[0048] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0049] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0050] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0051] The "unit" in the configuration of each of the above devices may be replaced with "means," "circuit," "device," etc.

[0052] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0053] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0054] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0055] 10: Information processing device, 11: Acquisition unit, 12: Memory unit, 13: Generation unit, 14: Calculation unit, 15: Output unit, 1001: Processor, 1002: Memory, 1003: Storage, 1004: Communication device, 1005: Input device, 1006: Output device.

Claims

1. An information processing device comprising: an acquisition unit that acquires new campaign information including information on stores that will be running a new campaign that is scheduled to be run and the business type to which each of the stores belongs; a hierarchical Bayes model that includes stores that have run multiple campaigns in the past and the business type to which each of the stores belongs, each at a different hierarchical level; a calculation unit that uses the acquired new campaign information to calculate effectiveness information regarding the effectiveness of the new campaign; and an output unit that outputs the calculated effectiveness information.

2. In the hierarchical Bayesian model, y i Let be the estimate of the causal effect of each campaign, and θ i is the mean, and σ i 2 When y is the variance, i ~N(θ i , σ i 2 ) and z ai is the j-dimensional store dummy variable, z bi is the i-dimensional business type dummy variable, x i are other explanatory variables, α is the intercept, and θ a is the store effect, θ b is the business type effect, β is x i When the coefficient of θ i = α + θ a T z ai +θ b T z bi +β T x i θ aj ~(0,τ a 2 ),j=1,…,J θ bk ~(0,τ b 2 2. The information processing apparatus according to claim 1, wherein k=1, . . . , K.

3. The store effect θ a and the business effect θ b 3. The information processing apparatus according to claim 2, wherein the prior distribution for .times. ...

4. The information processing device according to claim 1, further comprising a generation unit that generates the hierarchical Bayesian model using information about the stores that have implemented multiple campaigns in the past and the business types to which those stores belong, and information about the effectiveness of each of those campaigns.

5. An information processing method comprising: an acquisition step of acquiring new campaign information including information on stores that will be implementing a new campaign that is scheduled to be implemented and the business type to which each of said stores belongs; a calculation step of calculating effectiveness information regarding the effectiveness of said new campaign using a hierarchical Bayes model that includes stores that have implemented multiple campaigns in the past and the business type to which each of said stores belongs, each at a different hierarchical level, and the acquired new campaign information; and an output step of outputting the calculated effectiveness information.

Images