WO2018061136A1 - Procédé de prévision de la demande, système de prévision de la demande, et programme associé - Google Patents

Procédé de prévision de la demande, système de prévision de la demande, et programme associé Download PDF

Info

Publication number
WO2018061136A1
WO2018061136A1 PCT/JP2016/078756 JP2016078756W WO2018061136A1 WO 2018061136 A1 WO2018061136 A1 WO 2018061136A1 JP 2016078756 W JP2016078756 W JP 2016078756W WO 2018061136 A1 WO2018061136 A1 WO 2018061136A1
Authority
WO
WIPO (PCT)
Prior art keywords
sales
external data
product
prediction
correlation
Prior art date
Application number
PCT/JP2016/078756
Other languages
English (en)
Japanese (ja)
Inventor
幸生 中野
悠介 森田
壮太 佐藤
真佑子 美濃部
Original Assignee
株式会社日立製作所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社日立製作所 filed Critical 株式会社日立製作所
Priority to JP2018541798A priority Critical patent/JP6697082B2/ja
Priority to PCT/JP2016/078756 priority patent/WO2018061136A1/fr
Publication of WO2018061136A1 publication Critical patent/WO2018061136A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions

Definitions

  • the present invention relates to a method for predicting demand for goods.
  • a convenience store that sells a wide variety of products has a small store space and cannot hold a large amount of inventory. Therefore, by replenishing the goods during the day, the stock quantity is reduced while enhancing the product assortment.
  • the sales forecast value may be larger than the actual sales quantity, the number of stocks will increase (increase in bad stock, loss of daily items discarded), and profit will be reduced.
  • the predicted value of the sales volume is smaller than the actual sales volume, an opportunity loss due to out of stock occurs.
  • Patent Document 1 Japanese Patent Application Laid-Open No. 2001-216372 discloses a sales data database for storing sales data for each product obtained from a plurality of POS terminals to a host computer, and sales data stored in the database.
  • the high-speed search engine that extracts products whose sales have increased or decreased rapidly, and the products extracted by the high-speed search engine are set as search target products (product item, price range, etc), and the sales trends match
  • an extraction application that causes a high-speed search engine to search for a product having past sales data that approximates, and uses the past sales data of the product extracted by the search to create future sales prediction data of the target product for sales.
  • a prediction server of a POS support system provided.
  • the deviation between the forecast and the actual result is determined on a daily basis based on the sales results collected by the nighttime batch processing, and the forecast when the deviation occurs is corrected. It is difficult to correct and replenish the goods.
  • the present invention it is possible to detect a difference between the actual value and the predicted value of the event (number of customers or environment (precipitation, temperature, etc.) data) that causes the sales change, and appropriately correct the sales forecast of the product. Objective.
  • a typical example of the invention disclosed in the present application is as follows. That is, a demand prediction method executed by a demand prediction system configured by a computer, wherein the computer includes a processor that executes a program and a storage device that is accessed by the processor, and the demand prediction method includes: A monitoring step in which a processor collects actual values of external data representing an event affecting sales of the product and compares the actual values with the predicted values of the external data; and the processor includes the actual values and the predicted values. And a correction step of correcting the sales forecast of the product.
  • FIG. 3 is a flowchart of correlation analysis processing according to the first embodiment. It is a graph which shows the number of sales of the goods of Example 1. FIG. It is a graph which shows the number of customers of Example 1. 3 is an equation for calculating a correlation coefficient according to the first embodiment.
  • FIG. It is a figure which shows the correlation of the goods A and goods B of Example 1, and the number of visitors. It is a figure which shows the structural example of the sales and external data correlation information of Example 1.
  • FIG. It is a flowchart of the sales prediction process of Example 1. It is a flowchart of the performance value monitoring process of Example 1. It is a figure for demonstrating the performance value monitoring process of Example 1.
  • FIG. It is a flowchart of the prediction correction
  • FIG. It is a flowchart of the sales number re-prediction process of Example 1. It is a figure for demonstrating the sales number re-prediction process of Example 1.
  • FIG. It is a figure which shows the process which a client performs after the alert issue of Example 1.
  • FIG. 10 is a flowchart of correlation analysis processing according to the second embodiment. It is a figure which shows the structural example of the sales and external data correlation information of Example 2.
  • FIG. It is a flowchart of the performance value monitoring process of Example 2. It is a figure for demonstrating the performance value monitoring process of Example 2.
  • FIG. It is a flowchart of the 1st step prediction correction
  • FIG. It is a flowchart of the 2nd step prediction correction
  • FIG. 1 is a diagram illustrating a logical configuration of the analysis / prediction server 100 according to the first embodiment of this invention.
  • the analysis / prediction server 100 includes a data collection unit 110, a correlation analysis unit 120, a sales prediction unit 130, a performance value monitoring unit 141, a prediction correction target product selection unit 142, and a product sales prediction correction unit 143. That is, a demand prediction system that predicts demand) is configured. Each of these units is stored in the memory 12 as a server program 16 described later with reference to FIG. The function of each unit is realized by the processor 11 executing the server program 16.
  • the data collection unit 110 includes a POS data collection unit 111 and an external data collection unit 112.
  • the POS data collection unit 111 collects POS data 180 (sales result data 181) from the POS system 300.
  • the sales performance data 181 may be acquired from a system (for example, a sales management system) that accumulates equivalent information other than the POS system 300.
  • the external data collection unit 112 collects external data 190 that affects the sales of products from the external data providing system 400.
  • the external data 190 is, for example, store visitor number data 191 collected by a sensor installed in a store.
  • the external data 190 is so-called causal data, and may be environmental data such as precipitation data 192 and temperature data 193, for example. Further, as the external data, the number of customers, precipitation, and temperature are exemplified, but data of other events that affect the sales of products such as atmospheric pressure, humidity, wind speed, and sunshine hours may be used.
  • the correlation analysis unit 120 analyzes the external data 190 and the sales performance data 181 and extracts products whose external data and sales are correlated. As will be described later with reference to FIG. 5, the details of the process executed by the correlation analysis unit 120 may be executed in advance before executing the demand prediction and repeatedly (for example, at predetermined time intervals). The correlation between the external data and the sales derived by the correlation analysis unit 120 is registered in the correlation analysis result 150 as sales / external data correlation information 151. A configuration example of the sales / external data correlation information 151 will be described later with reference to FIG.
  • the correlation analysis result may be generated by another system without being generated by the analysis / prediction server 100.
  • the analysis / prediction server 100 does not need to implement the correlation analysis unit 120.
  • the sales forecasting unit 130 predicts sales of external data and products after the next day. Details of the processing executed by the sales prediction unit 130 will be described later with reference to FIG.
  • the prediction result derived by the sales prediction unit 130 is registered in the previous day prediction result 160 as sales prediction data 161 and external data prediction information 162.
  • external data and sales forecasts may be generated by other systems without being generated by the analysis / prediction server 100.
  • the analysis / prediction server 100 does not have to implement the sales prediction unit 130.
  • the actual value monitoring unit 141 acquires the actual value of the external data on the current day, compares it with the external data prediction information 162, and monitors whether a deviation has occurred. Details of the process executed by the actual value monitoring unit 141 will be described later with reference to FIG.
  • the prediction correction target product selection unit 142 selects a product that needs to be corrected for the sales forecast when a difference occurs between the actual value of the external data 190 and the external data prediction information 162. Details of the process executed by the prediction correction target product selection unit 142 will be described later with reference to FIG.
  • the product sales forecast correction unit 143 re-predicts the product sales of the corresponding product. Details of the processing executed by the merchandise sales forecast correction unit 143 will be described later with reference to FIG.
  • the prediction result derived by the product sales prediction correction unit 143 is registered in the prediction correction result 170 as sales re-prediction information 171.
  • the correlation analysis result 150, the previous day prediction result 160, and the prediction correction result 170 are data used by the analysis / prediction server 100 when executing the program, and are stored in the external storage device 500.
  • FIG. 2 is a diagram illustrating a configuration example of the sales performance data 181 according to the first embodiment.
  • the sales performance data 181 represents the actual value of the number of merchandise sales in a predetermined time unit (for example, every hour). Specifically, the sales performance data 181 includes data of date, time zone, store NO, product NO, and sales quantity, and the product indicated by the product NO in the store indicated by the store NO in the time zone indicated by the date and time. Stores the number of sales data. The number of sales can be generated by aggregating POS data acquired from the POS system 300 by time zone, store, and product.
  • FIG. 3A is a diagram illustrating a configuration example of the store visitor data 191 according to the first embodiment.
  • the store visitor number data 191 indicates the actual value of the store visitor number in a predetermined time unit (for example, every hour). Specifically, the store visitor data 191 includes date, time zone, store NO and store visitor data, and stores store store data indicated by the store NO in the time zone indicated by the date and time. To do.
  • the store visitor data 191 shown in FIG. 3A shows the actual value of the visitor count in each time slot from 10:00 to 24:00 on each day of March 8th and 9th, 2016 in a store whose store number is 100. Record.
  • the number of visitors can be counted by a sensor provided at the entrance of the store. Also, the number of visitors by sex and age may be collected by identifying the facial images of the customers taken by a camera installed at the entrance of the store.
  • FIG. 3B is a diagram illustrating a configuration example of precipitation data 192 and temperature data 193 according to the first embodiment.
  • the number of customers in a predetermined time unit indicates the actual value.
  • the precipitation data 192 and the temperature data 193 include date, time zone, precipitation and temperature data, and store precipitation and temperature data in the time zone indicated by the date and time.
  • the precipitation data 192 and the temperature data 193 may have data for each store (each region where the store is located).
  • the precipitation data 192 and temperature data 193 shown in FIG. 3B record precipitation and temperature measurements for each time zone from 10:00 to 24:00 on March 8th and 9th, 2016.
  • Precipitation and temperature environmental data can be provided by weather information service companies (such as forecasting business permit operators) and the Japan Meteorological Agency.
  • FIG. 4 is a diagram illustrating a physical configuration of a computer system including the analysis / prediction server 100 according to the first embodiment.
  • the computer system includes an analysis / prediction server 100, a client 200, a POS system 300, and an external data providing system 400.
  • the analysis / prediction server 100 is configured by a computer having a processor (CPU) 11, a memory 12, an auxiliary storage device 13, a communication control device 14, and an I / O control device 15.
  • the processor 11 executes the server program 16 stored in the memory 12.
  • the memory 12 includes a ROM that is a nonvolatile storage device and a RAM that is a volatile storage device.
  • the ROM stores an immutable program (for example, BIOS).
  • BIOS basic input/output
  • the RAM is a high-speed and volatile storage device such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor 11 and data used when the program is executed.
  • the I / O control device 15 connects the auxiliary storage device 13.
  • the auxiliary storage device 13 is configured by a large-capacity and non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD), for example, and stores a program executed by the processor 11 and data used when the program is executed. Store. Specifically, the auxiliary storage device 13 stores a correlation analysis result 150, a previous day prediction result 160, a prediction correction result 170, POS data 180, and external data 190. The program is read from the auxiliary storage device 13, loaded into the memory 12, and executed by the processor 11.
  • HDD magnetic storage device
  • SSD flash memory
  • the auxiliary storage device 13 is also a storage device provided inside the analysis / prediction server 100, and is connected to the analysis / prediction server 100 via a communication line (Ethernet, fiber channel, SATA, etc.) and provided separately.
  • An external storage device for example, Network Attached Storage may be used.
  • the communication control device 14 is a network interface device that controls communication with other devices (client 200, POS system 300, external data providing system 400, etc.) according to a predetermined protocol.
  • a program executed by the processor 11 is provided to the analysis / prediction server 100 via a removable medium (CD-ROM, flash memory, etc.) or a network, and is stored in a nonvolatile auxiliary storage device 13 which is a non-temporary storage medium.
  • the analysis / prediction server 100 may have an interface for reading data from the removable medium.
  • the analysis / prediction server 100 is a computer system configured on a plurality of computers that are physically configured on one computer or logically or physically, and is constructed on a plurality of physical computer resources. It may operate on a virtual machine. Further, the program executed on the analysis / prediction server 100 may operate in a separate thread on the same computer.
  • all or a part of the functional blocks implemented by the program may be configured by a physical integrated circuit (for example, Field-Programmable Gate Array).
  • the client 200 is constituted by a computer having a processor (CPU) 21, a memory 22, a communication control device 24, an I / O control device 25, an input device 27, and an output device 28, and is installed in a store, for example.
  • the analysis / prediction server 100 can be accessed and the analysis result by the analysis / prediction server 100 can be viewed. Note that the user may see information on other stores depending on the authority.
  • the processor 21 executes the application program 26 stored in the memory 22.
  • the memory 22 includes a ROM that is a nonvolatile storage device and a RAM that is a volatile storage device.
  • the ROM stores an immutable program (for example, BIOS).
  • BIOS basic input/output
  • the RAM is a high-speed and volatile storage device such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor 21 and data used when the program is executed.
  • the application program 26 may be a web browser that provides a user interface or a dedicated program.
  • the communication control device 24 is a network interface device that controls communication with other devices (such as the analysis / prediction server 100) according to a predetermined protocol.
  • the I / O control device 25 is an I / O interface that connects the input device 27 and the output device 28.
  • the input device 27 is a keyboard, a touch panel, a mouse, or the like, and is an interface that receives input from the user.
  • the output device 28 is a display device (for example, a liquid crystal display device), a printer, or the like, and is an interface that outputs the execution result of the program in a format that can be visually recognized by the user.
  • the output device 28 outputs, for example, a previous day prediction result, a current day actual value, a deviation occurrence alert, a prediction correction result, and the like.
  • the POS system 300 is a merchandise sales information management system installed in a store, and records merchandise sales information.
  • the POS system 300 is connected to the analysis / prediction server 100 via a network, and provides sales result data of accumulated products in response to a request from the analysis / prediction server 100.
  • the external data providing system 400 is a system that provides environmental data such as precipitation and temperature, and is operated by a weather information service company (such as a forecasting business permit business operator).
  • the external data providing system 400 is a store management system that counts the number of customers visiting the store.
  • FIG. 5 is a flowchart of the correlation analysis process of the first embodiment.
  • the correlation analysis processing is executed for each product by the correlation analysis unit 120 at a predetermined timing (a predetermined time interval such as weekly or monthly).
  • the correlation analysis unit 120 refers to the sales performance data 181 and the external data 190 (visitor data 191, precipitation data 192, temperature data 193) for each product. It is determined whether the increase or decrease in data is correlated, and a product for which sales and external data are correlated is selected (1001).
  • the sales of product A will increase or decrease with the increase in the number of visitors.
  • the sales of the product B are constant without being affected by the increase or decrease in the number of customers. In this case, it can be said that the product A has a correlation with the number of customers and the product B has no correlation with the number of customers.
  • the correlation between two values is calculated by calculating the correlation coefficient using a general statistical method. If the absolute value of the correlation coefficient is greater than a predetermined value (eg, 0.4), it is determined that there is a correlation. You can do it.
  • a predetermined value e.g, 0.4
  • the correlation coefficient can be calculated by the equation shown in FIG. 7A, for example.
  • the correlation coefficient between the sales of product A, the sales of product B, and the number of customers is calculated as shown in FIG. 7B, and the correlation coefficient between the sales of product A and the number of customers is 0.712308.
  • the correlation coefficient between the sales of B and the number of customers is -0.172262028. Therefore, it is determined that there is a correlation between the sales of the product A and the number of visitors, and there is no correlation between the sales of the product B and the number of visitors.
  • the correlation analysis unit 120 registers the product number of the selected product in the sales / external data correlation information 151 as a correlation analysis result (1002).
  • the sales / external data correlation information 151 as shown in FIG. 8, the type of external data and the product number of the product in which the external data and sales correlate are registered.
  • FIG. 5 shows an example of the correlation analysis process
  • various other methods can be employed.
  • the analysis / prediction server 100 may use a correlation analysis result generated by another system.
  • FIG. 9 is a flowchart of the sales prediction process of the first embodiment.
  • the sales prediction process is executed for each product by the sales prediction unit 130 at a predetermined timing (daily, predetermined time).
  • the sales prediction unit 130 predicts external data and sales of products on the target date (for example, the next day).
  • the sales forecasting unit 130 obtains forecast information on precipitation and temperature on the target day from the weather information service company, and predicts each value of external data (number of visitors, precipitation, temperature) on the target day,
  • the external data prediction information 162 is generated (1011).
  • the sales prediction unit 130 searches the past external data 190 for a day similar to the precipitation and temperature of the target day (1012). You may search for a day with similar external data on the condition of the season and day of the week.
  • the number of visitors on the day similar to the precipitation and temperature on the target day is extracted from the visitor number information 101 to predict the number of visitors on the target day.
  • the derived prediction of the number of customers is registered in the external data prediction information 162.
  • the sales of each product on the searched day is acquired from the sales performance data 181 and is set as the product sales forecast for the target date (1013).
  • the derived product sales forecast is registered in the sales forecast data 161.
  • FIG. 9 shows an example of the sales prediction process
  • various other methods can be adopted. For example, a calculation formula for predicting sales from the number of customers may be created, and sales may be predicted using the calculation formula. Sales may also be predicted by deep learning.
  • the analysis / prediction server 100 may use external data and sales prediction generated by another system.
  • FIG. 10A is a flowchart of actual value monitoring processing of the first embodiment.
  • the actual value monitoring process is executed by the actual value monitoring unit 141 at a predetermined timing (for example, the timing at which the external data actual value is acquired).
  • the actual value monitoring unit 141 acquires a real-time external data actual value at a predetermined timing (for example, every hour), and compares the external data actual value with an external data predicted value (1021). Then, the actual value monitoring unit 141 determines whether the actual value is within a predetermined error range from the predicted value (1022). As a result, the actual value monitoring unit 141 determines that no divergence has occurred if the actual value is within a predetermined error range from the predicted value, returns to step 1021, and returns the actual value and the predicted value at the next predetermined timing. The process is repeated to compare with. On the other hand, the actual value monitoring unit 141 determines that a divergence has occurred if the actual value exceeds a predetermined error range from the predicted value, and issues an divergence occurrence alert (1023).
  • the actual value is within the error range of the predicted value until 15:00, but exceeded the error range at 16:00. publish.
  • the error range that is a criterion for deviation may be fixed, may vary depending on the product, or may vary depending on other conditions (for example, time zone).
  • FIG. 11 is a flowchart of prediction correction target product selection processing according to the first embodiment.
  • the prediction correction target product selection process is executed by the prediction correction target product selection unit 142 at a timing when a deviation occurrence alert is issued in the actual value monitoring process.
  • the product whose sales are correlated with the external data where the divergence occurs is selected from the sales / external data correlation information 151 (1031). For example, in the example shown in FIG. 10B, a product with sales similar to the number of customers at 16:00 is selected.
  • FIG. 12 is a flowchart of the sales number re-prediction process according to the first embodiment.
  • the sales re-prediction process is executed by the product sales prediction correction unit 143 at the timing when the external data in which the divergence occurs and the product whose sales are correlated are extracted in the prediction correction target product extraction process.
  • the product sales forecast correction unit 143 searches the past external data for a date similar to the actual value of the external data up to the present time, and sets it as external data re-prediction information (1041). Specifically, as shown in FIG. 13, the past external data is searched for a date on which the actual value up to the present day of the day is within the allowable range of the past external data actual value. Then, the sales of each product on the retrieved day is acquired from the sales performance data 181 and is set as a new product sales forecast (1042).
  • the search range of the past day which is the actual value similar to the actual value on the day, may be fixed, may vary depending on the product, or may vary depending on other conditions (for example, time zone).
  • a calculation formula for predicting sales may be created from external data, and sales may be predicted using the calculation formula.
  • FIG. 14 is a diagram illustrating processing executed by the client after the alert is issued according to the first embodiment.
  • the client 200 refers to the sales forecast data 161 of the next day created by the analysis / prediction server 100, creates a product replenishment plan, and reserves delivery of the product (1101).
  • sales re-prediction information 171 of the prediction correction result 170 is generated.
  • the client 200 refers to the sales re-prediction information 171, corrects the product replenishment plan, and reserves additional delivery of the product (1103).
  • the first embodiment of the present invention it is possible to predict the occurrence of a sales divergence before the actual divergence between the predicted value of sales and the actual value occurs, and to correct the predicted value of sales. For this reason, it is possible to dynamically review the sales plan, adjust the product replenishment amount, avoid loss of sales opportunities due to out of stock, and suppress excess inventory.
  • issuance of a divergence alert of external data results is executed step by step with a degree of divergence according to the degree of correlation.
  • FIG. 15 is a diagram illustrating a logical configuration of the analysis / prediction server 100 according to the second embodiment.
  • the analysis / prediction server 100 includes a data collection unit 110, a correlation analysis unit 120, a sales prediction unit 130, an actual value monitoring unit 141, a first-stage prediction correction target product selection unit 144, a second-stage prediction correction target product selection unit 145, and A product sales forecast correction unit 143 is included.
  • the correlation analysis unit 120 analyzes external data and sales, and extracts products whose external data and sales are correlated. As will be described later with reference to FIG. 16, the details of the processing executed by the correlation analysis unit 120 are preferably executed in advance before executing the demand prediction, and may be executed repeatedly (for example, at predetermined time intervals). Unlike the first embodiment, the correlation analysis unit 120 according to the second embodiment registers the degree of correlation between sales of products and external data in the sales / external data correlation information 151. A configuration example of the sales / external data correlation information 151 will be described later with reference to FIG.
  • the actual value monitoring unit 141 acquires the actual value of the external data on the current day, compares it with the external data prediction information, and monitors whether a deviation has occurred. Unlike the first embodiment, the actual value monitoring unit 141 according to the second embodiment issues alerts in stages according to the degree of deviation. Details of the process executed by the actual value monitoring unit 141 will be described later with reference to FIG.
  • the first step prediction correction target product selection unit 144 When the first stage prediction correction target product selection unit 144 and the second stage prediction correction target product selection unit 145 have a difference between the actual value of the external data on the day and the external data prediction information, the first step prediction correction target product selection unit 144 In addition, a product for which the sales forecast needs to be corrected is selected. Details of processing executed by the first stage prediction correction target product selection unit 144 will be described later with reference to FIG. 19, and details of processing executed by the second stage prediction correction target product selection unit 145 will be described later with reference to FIG.
  • FIG. 16 is a flowchart of the correlation analysis process of the second embodiment.
  • the correlation analysis processing is executed for each product by the correlation analysis unit 120 at a predetermined timing (a predetermined time interval such as weekly or monthly).
  • the correlation analysis unit 120 refers to the sales performance data 181 and the external data 190 (visitor data 191, precipitation data 192, temperature data 193) for each product. It is determined whether the increase or decrease in data correlates, and a product for which sales and external data are correlated is selected (1051). For example, when the absolute value of the correlation coefficient calculated by the equation shown in FIG. 7A is larger than a predetermined value (for example, 0.4), it is determined that there is a correlation.
  • a predetermined value for example, 0.4
  • the correlation analysis unit 120 calculates the degree of correlation between the sales of the selected product and external data (1052).
  • the correlation coefficient calculated in step 1051 may be ranked to obtain the degree of correlation. Specifically, when the absolute value of the correlation coefficient is larger than 0.4 and smaller than 0.7, the correlation degree is “medium”, and when the absolute value of the correlation coefficient is 0.7 or more, the correlation degree is “large”. And The degree of correlation may not be two ranks if it is a plurality of ranks.
  • the correlation analysis unit 120 registers the product number, the correlation coefficient, and the correlation degree of the selected product in the sales / external data correlation information 151 as a correlation analysis result (1053).
  • the sales / external data correlation information 151 as shown in FIG. 17, the type of external data, and the product number, correlation coefficient, and correlation degree of a product having a correlation between the external data and sales are registered.
  • the analysis / prediction server 100 may use a correlation analysis result generated by another system.
  • FIG. 18A is a flowchart of actual value monitoring processing according to the second embodiment.
  • the actual value monitoring process is executed by the actual value monitoring unit 141 at a predetermined timing (for example, the timing at which the external data actual value is acquired).
  • the actual value monitoring unit 141 acquires a real-time external data actual value at a predetermined timing (for example, every hour), and compares the external data actual value with an external data predicted value (1061). Then, the actual value monitoring unit 141 determines whether the actual value is within a predetermined first error range from the predicted value (1062). As a result, if the actual value is within the predetermined first error range from the predicted value, the actual value monitoring unit 141 determines that the first-stage divergence has not occurred, returns to step 1061, and returns to the next predetermined predetermined value. The process is repeated so that the actual value and the predicted value are compared at the timing.
  • the actual value monitoring unit 141 determines that a first-stage divergence has occurred if the actual value exceeds a predetermined first error range from the predicted value, and issues an alert of the first-stage divergence occurrence. It is issued (1063).
  • the actual value monitoring unit 141 compares the external data actual value with the external data predicted value (1064). Then, the actual value monitoring unit 141 determines whether the actual value is within a predetermined second error range from the predicted value (1065). As a result, if the actual value is within the predetermined second error range from the predicted value, the actual value monitoring unit 141 determines that the second-stage divergence has not occurred, returns to step 1041, and returns to the next predetermined The process is repeated so that the actual value and the predicted value are compared at the timing. On the other hand, if the actual value exceeds the predetermined second error range from the predicted value, the actual value monitoring unit 141 determines that a second-stage divergence has occurred, and issues a second-stage divergence alert. It is issued (1066).
  • the actual value is within the error range of the predicted value until 15:00, but exceeded the first error range of ⁇ 7% at 16:00, but ⁇ 13% Since the second error range is not exceeded, it is determined that a first-stage divergence has occurred, and a first-stage divergence occurrence alert is issued. Further, since the second error range of ⁇ 13% is exceeded at 17:00, it is determined that a second-stage divergence has occurred, and a second-stage divergence occurrence alert is issued.
  • FIG. 19 is a flowchart of the first stage prediction correction target product extraction process.
  • the first-stage prediction correction target product extraction process is executed by the first-stage prediction correction target product selection unit 144 at the timing when the first-stage divergence alert is issued in the actual value monitoring process.
  • a product having a large correlation degree is selected from the sales / external data correlation information 151 (1071). For example, in the example shown in FIG. 10B, at the time of 16:00, a product with a similar correlation between the number of customers and the sales is selected.
  • FIG. 20 is a flowchart of the second stage prediction correction target product extraction process.
  • the second-stage prediction correction target product extraction process is executed by the second-stage prediction correction target product selection unit 145 when the second-stage divergence occurrence alert is issued in the actual value monitoring process.
  • the external data in which the second-stage divergence has occurred and sales are correlated, and a product having a medium correlation is selected from the sales / external data correlation information 151 (1081). For example, in the example shown in FIG. 10B, at the time of 17:00, the number of customers and the sales tendency are similar, and a product with a medium correlation is selected.
  • the first-stage prediction correction target product selection unit 144 uses the correlation in order to correct the sales prediction at an early stage for a highly correlated product even when the degree of deviation of the actual value of the external data is small. Select products with a high degree.
  • the second-stage prediction correction target product selection unit 145 selects a product with a medium correlation degree in order to correct the sales prediction of a product with low correlation when the degree of deviation of the actual value of the external data is large. To do.
  • Example 2 as long as the discrepancy between the actual value and the predicted value of the external data is small, as a first step, the sales prediction of the product having a large correlation between the external data and the sales is reviewed. Further, when the discrepancy between the actual value and the predicted value of the external data becomes large, as a second step, the sales prediction of the product having a low correlation degree (medium correlation) is reviewed. For this reason, in the second embodiment, by delaying the review of sales of products whose sales do not respond so sensitively to external data, the number of products to be reviewed at the same time can be reduced, and the concentration of processing load on the analysis / prediction server 100 can be reduced.
  • the degree of correlation is not large in the second stage (the correlation is It will review the sales forecast for only the (medium) product.
  • the discrepancy between the external data and the predicted value suddenly increases, if the sales forecast for a product with a high degree of correlation has not been reviewed in the first stage, the correlation between the product with a high degree of correlation and the degree of correlation will be given in the second stage. Review sales forecasts for products that are not large (medium correlation).
  • the demand prediction system (analysis / prediction server 100) according to the present embodiment collects external data (actual value) 190 representing an event that affects the sales of products, and external data (actual value) 190.
  • Value monitoring unit 141 that compares the external data prediction information 162 with the external data prediction information 162, and a product sales prediction correction unit that corrects the sales prediction data 161 of the product when it is determined that the actual data value and the prediction value of the external data are different 143, the sales forecast of the product can be appropriately corrected.
  • signs of divergence between the sales record and the sales forecast can be detected, and the sales forecast can be corrected early. For this reason, it is possible to arrange a change in the purchase quantity of the goods at an early stage, it is possible to suppress the occurrence of excess inventory, and it is possible to avoid opportunity loss due to out of stock.
  • the analysis / prediction server 100 holds the past sales (sales result data 181) and external data (actual value) 190 of the product.
  • the analysis / prediction server 100 searches the past external data 190 whose tendency is similar to that of the external data prediction information 162, and sets the sales of the product on the day corresponding to the searched external data 190 as the sales prediction data 161 of the product. It has a sales forecasting unit 130. Further, if the product sales prediction correction unit 143 determines that the actual value of the external data used for the sales prediction is different from the predicted value, the product sales prediction correction unit 143 corrects the sales prediction of the product for which the external data and sales are correlated. Therefore, it is possible to appropriately correct the sales forecast of the product.
  • the analysis / prediction server 100 also selects a product for which the external data (actual value) 190 and the external data prediction information 162 are determined to be different from each other, and selects a product whose sales correlates with the external data.
  • the actual value monitoring unit 141 monitors whether the actual value and the predicted value of the external data deviate beyond a predetermined error range, and the product sales prediction correction unit 143 displays the sales prediction data of the selected product. 161 is corrected. For this reason, it is possible to appropriately correct the sales forecast of a product whose sales change according to external data.
  • the analysis / prediction server 100 holds past sales data (sales result data 181) and external data (actual value) 190 of the product. Further, the analysis / prediction server 100 includes a correlation analysis unit 120 that analyzes the correlation between the product sales and the external data with reference to the sales result data 181 and the external data (actual value) 190. Furthermore, the prediction correction target product selection unit 142 refers to the correlation between the product sales analyzed by the correlation analysis unit 120 and the external data, and the external data (actual value) 190 and the external data prediction information 162 are different. Therefore, it is possible to appropriately correct the sales forecast of the product.
  • the actual value monitoring unit 141 determines whether the external data (actual value) 141 and the external data prediction information 162 deviate beyond a plurality of predetermined error ranges (first error range, second error range). To monitor.
  • the first stage prediction correction target product selection unit 144 refers to the monitoring result of the first error range and the degree of correlation between the external data and the sales, and the difference between the actual value of the external data and the predicted value is small. In this case, a product having a large correlation is selected, and the second stage prediction correction target product selection unit 145 refers to the monitoring result of the second error range and the degree of correlation between the external data and the sales, and the actual data of the external data.
  • the merchandise sales forecast correction unit 143 corrects the forecast of the sales of the merchandise having a large correlation when the deviation between the actual value of the external data and the forecast value is small, and the deviation between the actual value of the external data and the forecast value is If it is large, the forecast of sales of products with high correlation and products with low correlation is corrected, so by delaying the review of sales of products whose sales do not respond sensitively to changes in external data, the number of products reviewed at the same time is reduced and analyzed. The concentration of processing load on the prediction server 100 can be reduced.
  • the product sales prediction correction unit 143 searches for past external data whose tendency is similar to that of the external data (actual value) 190, and uses the product sales on the day corresponding to the searched external data, to Since the predicted value of is corrected, the sales forecast of the product can be corrected appropriately.
  • the present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the scope of the appended claims.
  • the above-described embodiments have been described in detail for easy understanding of the present invention, and the present invention is not necessarily limited to those having all the configurations described.
  • a part of the configuration of one embodiment may be replaced with the configuration of another embodiment.
  • another configuration may be added, deleted, or replaced.
  • each of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, with an integrated circuit, and the processor realizes each function. It may be realized by software by interpreting and executing the program to be executed.
  • Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, and an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, and a DVD.
  • a storage device such as a memory, a hard disk, and an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, and a DVD.
  • control lines and information lines indicate what is considered necessary for the explanation, and do not necessarily indicate all control lines and information lines necessary for mounting. In practice, it can be considered that almost all the components are connected to each other.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

La présente invention concerne un procédé de prévision de la demande mis en œuvre par un système de prévision de la demande comportant un ordinateur, l'ordinateur comprenant un processeur servant à exécuter un programme, et comprenant un dispositif de stockage auquel accède le processeur, le procédé de prévision de la demande comportant: une étape de surveillance lors de laquelle des valeurs de performances de données externes représentant des événements qui ont un effet sur les ventes d'une marchandise sont recueillies par le processeur, qui effectue à son tour des comparaisons entre les valeurs de performances et des valeurs prédites des données externes; et une étape de correction lors de laquelle, dans le cas où il est déterminé que les valeurs de performances et les valeurs prédites s'écartent les unes des autres, le processeur corrige une prévision de ventes de la marchandise.
PCT/JP2016/078756 2016-09-29 2016-09-29 Procédé de prévision de la demande, système de prévision de la demande, et programme associé WO2018061136A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2018541798A JP6697082B2 (ja) 2016-09-29 2016-09-29 需要予測方法、需要予測システム及びそのプログラム
PCT/JP2016/078756 WO2018061136A1 (fr) 2016-09-29 2016-09-29 Procédé de prévision de la demande, système de prévision de la demande, et programme associé

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2016/078756 WO2018061136A1 (fr) 2016-09-29 2016-09-29 Procédé de prévision de la demande, système de prévision de la demande, et programme associé

Publications (1)

Publication Number Publication Date
WO2018061136A1 true WO2018061136A1 (fr) 2018-04-05

Family

ID=61760200

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/078756 WO2018061136A1 (fr) 2016-09-29 2016-09-29 Procédé de prévision de la demande, système de prévision de la demande, et programme associé

Country Status (2)

Country Link
JP (1) JP6697082B2 (fr)
WO (1) WO2018061136A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112504348A (zh) * 2020-12-11 2021-03-16 厦门汇利伟业科技有限公司 一种融合环境因素的物体状态显示方法和系统
JP2023060144A (ja) * 2019-01-31 2023-04-27 三菱電機株式会社 照明制御システム
US20240168709A1 (en) * 2018-12-31 2024-05-23 Kevin D. Howard Computer Processing and Outcome Prediction Systems and Methods

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001216372A (ja) * 2000-01-31 2001-08-10 Toshiba Corp 売上げ予測装置、売上げ予測方法、記憶媒体
JP2002007671A (ja) * 2000-04-21 2002-01-11 Ns Solutions Corp 需要予測装置、方法、コンピュータプログラム、及びコンピュータ読み取り可能な記録媒体
JP2002024350A (ja) * 2000-07-03 2002-01-25 Kasumi Co Ltd 小売店舗管理システム
JP2003281348A (ja) * 2002-03-25 2003-10-03 Yunitekku:Kk 商圏分析システム、方法、プログラム、及び記録媒体
JP2004334326A (ja) * 2003-04-30 2004-11-25 Nri & Ncc Co Ltd 商品需要予測システム、商品の売上数調整システム
JP2008123371A (ja) * 2006-11-14 2008-05-29 Kose Corp 商品の需要予測装置および商品の需要予測方法ならびにそのプログラム

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004227321A (ja) * 2003-01-23 2004-08-12 Fujitsu Ltd 発注ガイダンス生成方法及び装置、発注方法並びにコンピュータプログラム
JP2007047996A (ja) * 2005-08-09 2007-02-22 Tokyo Electric Power Co Inc:The 需要予測装置及び方法並びにプログラム
JP2007316758A (ja) * 2006-05-23 2007-12-06 Toshiba Tec Corp 来店客数予測サーバ及び来店客数予測プログラム
JP6003736B2 (ja) * 2013-03-18 2016-10-05 富士通株式会社 情報処理プログラム、情報処理方法および情報処理装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001216372A (ja) * 2000-01-31 2001-08-10 Toshiba Corp 売上げ予測装置、売上げ予測方法、記憶媒体
JP2002007671A (ja) * 2000-04-21 2002-01-11 Ns Solutions Corp 需要予測装置、方法、コンピュータプログラム、及びコンピュータ読み取り可能な記録媒体
JP2002024350A (ja) * 2000-07-03 2002-01-25 Kasumi Co Ltd 小売店舗管理システム
JP2003281348A (ja) * 2002-03-25 2003-10-03 Yunitekku:Kk 商圏分析システム、方法、プログラム、及び記録媒体
JP2004334326A (ja) * 2003-04-30 2004-11-25 Nri & Ncc Co Ltd 商品需要予測システム、商品の売上数調整システム
JP2008123371A (ja) * 2006-11-14 2008-05-29 Kose Corp 商品の需要予測装置および商品の需要予測方法ならびにそのプログラム

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240168709A1 (en) * 2018-12-31 2024-05-23 Kevin D. Howard Computer Processing and Outcome Prediction Systems and Methods
JP2023060144A (ja) * 2019-01-31 2023-04-27 三菱電機株式会社 照明制御システム
JP7414168B2 (ja) 2019-01-31 2024-01-16 三菱電機株式会社 照明制御システム
CN112504348A (zh) * 2020-12-11 2021-03-16 厦门汇利伟业科技有限公司 一种融合环境因素的物体状态显示方法和系统

Also Published As

Publication number Publication date
JPWO2018061136A1 (ja) 2018-12-06
JP6697082B2 (ja) 2020-05-20

Similar Documents

Publication Publication Date Title
JP7021289B2 (ja) 資産情報のディスプレイ方法
US10372723B2 (en) Efficient query processing using histograms in a columnar database
US11790383B2 (en) System and method for selecting promotional products for retail
US11334845B2 (en) System and method for generating notification of an order delivery
US7437323B1 (en) Method and system for spot pricing via clustering based demand estimation
JP5963709B2 (ja) 計算機、予測方法、及び、予測プログラム
US12002063B2 (en) Method and system for generating ensemble demand forecasts
US10970263B1 (en) Computer system and method of initiative analysis using outlier identification
JP2005182465A (ja) 保守支援方法及びプログラム
US20150339600A1 (en) Method and system for analysing data
JP6697082B2 (ja) 需要予測方法、需要予測システム及びそのプログラム
US20220351051A1 (en) Analysis system, apparatus, control method, and program
US11403652B1 (en) Customer-level lifetime value
CN110688846B (zh) 周期词挖掘方法、系统、电子设备及可读存储介质
CA3182205A1 (fr) Evaluation de risque financier
JP5847137B2 (ja) 需要予測装置及びプログラム
US8417811B1 (en) Predicting hardware usage in a computing system
US20120323617A1 (en) Processing of business event data to determine business states
CN111340541A (zh) 酒店房型异常价格的预警方法、系统、设备和介质
JP6276655B2 (ja) 需要予測装置およびプログラム
US20160307218A1 (en) System and method for phased estimation and correction of promotion effects
WO2019059135A1 (fr) Dispositif de traitement d'informations, système de traitement d'informations, procédé de traitement d'informations et support d'enregistrement
US20190266548A1 (en) Project Progress Prediction Device and Project Progress Prediction System
JP2023104145A (ja) 計算機システム及び予測モデルの学習方法
JP2022190881A (ja) 施策提示装置、施策提示方法、および施策提示プログラム

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 2018541798

Country of ref document: JP

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16917688

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16917688

Country of ref document: EP

Kind code of ref document: A1