JP7040441B2 - Opportunity loss calculation system, opportunity loss calculation method and opportunity loss calculation program - Google Patents

Description

The present invention relates to an opportunity loss calculation system for calculating an opportunity loss of a product, an opportunity loss calculation method, and an opportunity loss calculation program.

It is common practice to forecast sales based on past sales performance. Opportunity loss may also be considered in past sales performance to further improve forecast accuracy.

An example of a method for calculating opportunity loss is described in Patent Document 1. In the method described in Patent Document 1, for the product to be predicted, the cumulative sales performance J (t) and the cumulative sales forecast Y (t) at the supply time point t are obtained for each supply cycle, and then R (t) =. The deviation amount R (t) between the supply amount and the demand amount is calculated by Y (t) -J (t).

Japanese Unexamined Patent Publication No. 10-228463

However, in reality, even if a certain target product does not exist, it cannot always be said that all the losses have occurred for the quantity predicted to be sold. For example, even if a type A beverage does not exist at a certain store, there is a good possibility that a type B beverage will be purchased instead. In this case, even if the type A beverage does not exist in a certain store, the sales of the beverage as a whole in the store do not change. In this way, just because a certain target product does not exist does not mean that an opportunity loss corresponding to the predicted quantity of the target product simply occurs.

As described in Patent Document 1, if the amount of deviation between the sales forecast and the sales performance of a certain target product is simply regarded as an opportunity loss, the opportunity loss is calculated for each product in the same manner. There is a risk of overestimating the opportunity loss of the store as a whole.

Therefore, an object of the present invention is to provide an opportunity loss calculation system, an opportunity loss calculation method, and an opportunity loss calculation program that can more appropriately calculate the opportunity loss of the store as a whole.

The opportunity loss calculation system according to the present invention is the number of demands without shortage and the number of demands thereof, which is the number of demands when the products included in the target product set are not out of stock, for each target product set including a plurality of products. A storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more of the products included in the target product set are out of stock, in association with each period, and the period in which a certain product is out of stock. The opportunity loss calculation unit is provided with an opportunity loss calculation unit that calculates the opportunity loss of the target product set including the product in the storage unit based on the number of demands without shortage and the number of demands with shortage in the corresponding period stored in the storage unit. The department is characterized in that the difference between the number of demands with shortages and the number of demands without shortages is calculated as an opportunity loss of the target product set .

The opportunity loss calculation method according to the present invention is the number of demands without shortage, which is the number of demands when the computer is not out of stock for the target product set including a plurality of products and the products included in the target product set are not out of stock. The period for calculating the opportunity loss from the storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more of the products included in the target product set are out of stock, in association with each period. The number of demands with shortages and the number of demands without shortages corresponding to the above are specified, and the computer calculates the opportunity loss of the target product set for the period from the difference between the specified number of demands without shortages and the number of demands with shortages. It is characterized by doing.

The opportunity loss calculation program according to the present invention is the number of demands without shortage, which is the number of demands when the products included in the target product set are not out of stock for each target product set containing a plurality of products. And the period for calculating the opportunity loss from the storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more of the products included in the target product set are out of stock, in association with each period. Specified processing to identify the number of demands with and without shortages corresponding to, and the opportunity loss of the target product set for the period is calculated based on the specified number of demands without shortages and the number of demands with shortages. It is characterized in that the calculation process is executed and the difference between the number of demands with missing items and the number of demands without missing items is calculated as the opportunity loss of the target product set in the opportunity loss calculation process.

According to the present invention, the opportunity loss of the store as a whole can be calculated more appropriately.

It is a block diagram which shows the structural example of the 1st Embodiment of the opportunity loss calculation system by this invention. It is explanatory drawing which shows the example of the opportunity loss. It is explanatory drawing which shows the example of the calculation method of the opportunity loss. It is explanatory drawing which shows the example of the demand number which a storage part 11 stores. It is explanatory drawing which shows the example of the process of calculating the opportunity loss. It is explanatory drawing which shows the example of the process which corrects the sales. It is a flowchart which shows the operation example of the opportunity loss calculation system of 1st Embodiment. It is explanatory drawing which shows the example of the situation where the demand shift occurs to another product set. It is explanatory drawing which shows the other example of the demand number which a storage part 11 stores. It is explanatory drawing which shows the example of the process which calculates the category demand shift. It is a flowchart which shows the operation example of the opportunity loss calculation system of 2nd Embodiment. It is a block diagram which shows the outline of the opportunity loss calculation system by this invention.

Embodiment 1.
FIG. 1 is a block diagram showing a configuration example of a first embodiment of the opportunity loss calculation system according to the present invention. The opportunity loss calculation system 10 of the present embodiment includes a storage unit 11, an opportunity loss calculation unit 12, a correction unit 13, a learning unit 14, and a prediction unit 15.

First, the opportunity loss assumed in the present invention will be described. FIG. 2 is an explanatory diagram showing an example of opportunity loss. If a single item A (single item A) is out of stock during a certain time period, the quantity of the single item A that could have been sold during that time period can be said to be an opportunity loss (see FIG. 2 (A)). The "out of stock" means, for example, a state in which the product is not displayed at the store. "Out of stock" means when the product is completely sold and out of stock, or when the person in charge of ordering forgets to place an order for the product, the manufacturer of the product is out of stock, shipping trouble, or the person in charge of display. This can happen if a person forgets to display the product.

FIG. 3 is an explanatory diagram showing an example of a method of calculating opportunity loss. For example, there are three products classified into the product category "Onigiri" sold in the time zone identified by the time zone ID "0" on a certain day (product A, product B and product C), and product A. Only out of stock. Assuming that the average number of past products A sold in the time zone identified by the time zone ID "0" is 3.0, the opportunity loss at that time is calculated to be 3.0.

On the other hand, it is known that a customer purchases another product as a substitute when one product is out of stock. Hereinafter, such a phenomenon will be referred to as a demand shift. For example, as illustrated in FIG. 2B, it is assumed that a plurality of product sets (for example, a single product A (single product A) and a single product B (single product B)) are classified into a certain classification α. Here, if the single item A is out of stock, the customer may purchase the single item B instead.

In this case, it can be said that a simple opportunity loss does not occur in the entire store because the shortage of the single item A leads to the purchase of the single item B. In the following description, the phenomenon in which a demand shift occurs within a certain product set (within the same category) is referred to as a single item demand shift. In addition, a phenomenon in which a customer leaves the store without a substitute purchase due to a shortage of the single item A without a shift in the demand for the single item is referred to as a complete opportunity loss.

For example, due to the shortage of the product A as illustrated in FIG. 3, the opportunity loss is calculated to be 3.0 when only the opportunity loss of the product A alone is considered. However, if the sales of the product C are increased by one instead due to the shortage of the product A, it can be judged that the complete opportunity loss is equivalent to 2.0 rice balls for the entire store. In this embodiment, the opportunity loss is calculated in the unit of the product set in this way.

The storage unit 11 stores the number of demands for each product set including a plurality of products in association with each period. The length of the period associated here is arbitrary. In this period, for example, one day may be divided into fixed time zones, or one year may be divided into monthly units, daily units, and the like. The number of demands is, for example, the average value of the number of sales of the product, is calculated from past actual data, and is stored in the storage unit 11 in advance. The storage unit 11 is realized by, for example, a magnetic disk or the like.

Further, in the storage unit 11, for each product set, the number of demands when the products included in the product set are not out of stock and one or more products included in the product set are out of stock. The number of demands when they were there is stored separately. In the following explanation, the number of demands when the products included in the product set are not out of stock is referred to as the number of demands without shortage, and the number of demands when one or more products included in the product set are out of stock. Is referred to as the number of out-of-stock items and demand. In the following description, the target product set for which the opportunity loss is calculated is referred to as a target product set.

A product set can include a plurality of arbitrary products. In addition, in order to appropriately calculate the opportunity loss of the store as a whole, it is preferable to define a product group that can be a candidate for an option when one product is out of stock as a product set. Examples of product sets include sets of products of the same type or category (for example, multiple types of rice balls, beverages, etc.).

Further, the storage unit 11 may store the number of shortages and demands for each period according to the pattern of shortages of the products included in the product set. The pattern of product shortages included in the product set can be considered as the square of the number of products, considering the presence or absence of products. However, it is preferable that the number of patterns is not too large so that the number of demands for each pattern can be calculated more accurately from the past actual data. The storage unit 11 may store, for example, the number of demands for each period according to the pattern of shortage of products having a higher number of sales in the product set. For example, in the case of the presence / absence pattern of the top three products, the number of demands for each period is eight patterns.

FIG. 4 is an explanatory diagram showing an example of the number of demands stored in the storage unit 11. In the example shown in FIG. 4, the storage unit 11 stores the number of demands (average value of the number of sales) for each time zone according to the pattern of inventory availability (out of stock) of the top three products (main products). Is shown. For example, pattern 7 shows a state in which the first-ranked main product is out of stock and the second-ranked main product and the third-ranked main product are in stock.

In other words, the pattern of product shortages included in the target product set is the state in which the products included in the product set are not out of stock, or one or more products included in the product set are missing. It can be said that it is information indicating the state of being in good condition. Then, it is assumed that the "number of demands according to the pattern" can be obtained by considering the demand shift even if some products in the target product set are out of stock in the state indicated by the pattern. Means the number of demands.

In addition, it is considered that the number of demands is maximized when all the products included in the target product set exist (that is, the products included in the product set are not out of stock). Therefore, in the present embodiment, the number of demands when the products included in the target product set are not out of stock (the number of demands without shortage) and one or more products included in the target product set are missing. Opportunity loss is calculated based on the number of demands when the product was in stock (the number of demands with shortages).

The opportunity loss calculation unit 12 calculates the opportunity loss of the target product set in the period when the product is out of stock based on the number of demands without shortage and the number of demands with out of stock in the corresponding period stored in the storage unit 11. Specifically, the opportunity loss calculation unit 12 calculates the difference between the number of demands with shortages and the number of demands without shortages as the opportunity loss of the target product set.

Further, when the storage unit 11 stores the number of shortages and demands for each period according to the pattern of shortages, the opportunity loss calculation unit 12 has no shortages in the period for calculating the opportunity loss of the target product set. The difference between the number of demands and the number of demands with shortages that match the pattern of product shortages during that period may be calculated as the opportunity loss of the target product set.

FIG. 5 is an explanatory diagram showing an example of processing for calculating opportunity loss. Table T1 exemplified in FIG. 5 is actual data of products belonging to the product category “rice ball” in the date “YY / MM / DD” of the store identified by the store CD “001”. FIG. 5 shows the actual data of the time zone identified by the time zone ID “0”. Further, Table T2 exemplified in FIG. 5 shows a pattern of presence / absence (out of stock) of the product. As shown in Table T1, the example shown in FIG. 5 corresponds to pattern 7 because the main product in the first place is out of stock and the main product in the second place and the main product in the third place are in stock. Further, the state in which all the products are in stock corresponds to pattern 8.

Further, Table T3 illustrated in FIG. 5 shows the number of demands for each period according to the pattern. In the example shown in FIG. 5, the average sales number of pattern 7 in the time zone identified by the time zone “0” is 8.0 (pieces), and the average sales number of pattern 8 is 9.0 (pieces). Is.

Therefore, the opportunity loss calculation unit 12 sets the opportunity loss of the target product set in the period when the product is out of stock (that is, the time zone identified by the time zone “0”) as the number of demands with out of stock (8) in the corresponding period. Calculated by the difference between 0.0 (pieces)) and the number of demands without shortages (9.0 (pieces)). Here, the difference is calculated as one. As illustrated in Table T3, the opportunity loss calculation unit 12 uses the calculated value as the opportunity loss of the target product set.

The correction unit 13 corrects the sales of the target product set during the period when a certain product is out of stock by using the calculated opportunity loss. Specifically, the correction unit 13 adds the calculated opportunity loss to the sales of the target product set.

FIG. 6 is an explanatory diagram showing an example of a process for correcting sales. Table T4 illustrated in FIG. 6 shows the data before correction due to opportunity loss, and Table T5 exemplified in FIG. 6 shows the data after correction using opportunity loss. For example, in the example shown in FIG. 5, the opportunity loss of pattern 7 is calculated as one in the rice ball category, which is the target product set. Therefore, the correction unit 13 corrects the opportunity loss (1 piece) by adding it to the number of sales, which is the sales of the entire rice ball category in the corresponding time zone.

By making such a correction, the learning unit 14 described later can learn the prediction model in consideration of the opportunity loss.

The learning unit 14 performs learning using the data including the corrected sales, and creates a demand forecast model for the target product set. The learning method is arbitrary, and a widely known and general method may be used.

The forecasting unit 15 predicts the demand of the target product set by using the created demand forecast model. For example, when the target product set is rice balls, the prediction unit 15 predicts the demand for the entire rice balls. Further, the forecasting unit 15 may calculate the demand forecast of each product included in the target product set based on the forecast result. For example, when the average value of the number of sales of each product in the past fixed period is calculated, the forecasting unit 15 prorates the calculated forecast result (number of demands) according to the ratio of the average value of the number of sales of each product. You may.

The opportunity loss calculation unit 12, the correction unit 13, the learning unit 14, and the prediction unit 15 are realized by a computer CPU that operates according to a program (opportunity loss calculation program). For example, the program may be stored in the storage unit 11, and the CPU may read the program and operate as the opportunity loss calculation unit 12, the correction unit 13, the learning unit 14, and the prediction unit 15 according to the program. Further, the function of the opportunity loss calculation system 10 may be provided in the SAAS (Software as a Service) format.

Further, the opportunity loss calculation unit 12, the correction unit 13, the learning unit 14, and the prediction unit 15 may be realized by dedicated hardware, respectively. Further, a part or all of each component of each device may be realized by a general-purpose or dedicated circuitry, a processor, or a combination thereof. These may be composed of a single chip or may be composed of a plurality of chips connected via a bus. A part or all of each component of each device may be realized by the combination of the circuit or the like and the program described above.

Further, when a part or all of each component of each device is realized by a plurality of information processing devices and circuits, the plurality of information processing devices and circuits may be centrally arranged or distributed. May be done. For example, the information processing device, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client-and-server system and a cloud computing system.

Next, an operation example of the opportunity loss calculation system of this embodiment will be described. FIG. 7 is a flowchart showing an operation example of the opportunity loss calculation system of the present embodiment. Here, it is assumed that the opportunity loss of sales of a product set during a period when a certain product is out of stock is calculated. The opportunity loss calculation unit 12 specifies from the storage unit 11 the number of demands with shortages and the number of demands without shortages corresponding to the period for calculating the opportunity loss (step S11). When the storage unit 11 stores the number of out-of-stock items and the number of demands for each period according to the pattern of out-of-stock items, the opportunity loss calculation unit 12 is out of stock that matches the pattern of out-of-stocks of the products in the corresponding period. It is only necessary to specify the number of demands.

Then, the opportunity loss calculation unit 12 calculates the opportunity loss of the target product set during that period based on the specified number of demands without shortages and the number of demands with shortages (step S12). The opportunity loss calculation unit 12 may calculate, for example, the difference between the number of demands without shortages and the number of demands with shortages as the opportunity loss of the target product set.

The correction unit 13 corrects the sales of the target product set by using the calculated opportunity loss (step S13). The learning unit 14 performs learning using the corrected data, and creates a demand forecast model for the target product set (step S14). The forecasting unit 15 predicts the demand of the target product set by using the created demand forecast model (step S15).

As described above, in the present embodiment, the opportunity loss calculation unit 12 stores the opportunity loss from the storage unit 11 that stores the number of demands without shortage and the number of demands with shortage for each target product set in association with each period. The number of demands with shortages and the number of demands without shortages corresponding to the calculated period are specified, and the opportunity loss of the target product set is calculated based on the specified number of demands without shortages and the number of demands with shortages. Therefore, the opportunity loss of the store as a whole can be calculated more appropriately.

That is, in the present embodiment, the opportunity loss of the entire store is more appropriately calculated because the opportunity loss is calculated for each set of products in which the demand shift is expected to occur, instead of calculating the opportunity loss of each product. Can be calculated.

Embodiment 2.
Next, a second embodiment of the opportunity loss calculation system of the present invention will be described. The configuration of the opportunity loss calculation system of this embodiment is the same as that of the first embodiment. In the present embodiment, the opportunity loss is calculated in consideration of not only the single item demand shift but also the situation where the demand shift occurs to a product set different from the classified product set (that is, a product set having a different type or category).

FIG. 8 is an explanatory diagram showing an example of a situation in which a demand shift occurs to another product set. In FIG. 8, the set of products belonging to the classification α is referred to as the product set α, and the set of products classified separately from the classification α is referred to as the product set β.

As in the case illustrated in FIG. 2, it is assumed that a plurality of products (for example, a single product A (single product A) and a single product B (single product B)) are classified into a certain classification α. Here, if the single item A is out of stock, the customer may purchase the single item B instead. In addition, the customer may purchase a single product C (single product C) classified into another category β instead of a product classified into the same category α. Since a product set can be said to be a set of products classified by some category, in the following description, a phenomenon in which a demand shift occurs across a certain product set is referred to as a category demand shift.

The storage unit 11 stores the same number of demands as in the first embodiment. Further, the storage unit 11 of the present embodiment stores the number of demands of other product sets in association with each other when the products included in the target product set are not out of stock. Hereinafter, this number of demands will be referred to as the first number of demands. Further, the storage unit 11 stores the number of demands of another product set when the product included in the target product set is out of stock in association with each other. Hereinafter, this number of demands will be referred to as the second number of demands.

When the storage unit 11 stores the number of out-of-stock items and the number of demands for each period according to the out-of-stock pattern, the storage unit 11 is in the case where the out-of-stock state of the target product set is indicated by the out-of-stock pattern. The number of demands of other product sets may be stored in association with each other.

FIG. 9 is an explanatory diagram showing another example of the number of demands stored in the storage unit 11. In the example shown in FIG. 9, it is shown that the storage unit 11 stores the average value of the number of sales of the product set (classification β) different from the target product set as the actual value. Here, the storage unit 11 stores the average value of the number of sales of the classification β in the case of the pattern (1 to 8) of the target product set in association with each other. For example, when the product pattern of the target product set is 7 in the time zone identified by the time zone ID “0”, the average value of the number of sales of the classification β is 1.1.

The opportunity loss calculation unit 12 calculates the opportunity loss for each product set as in the first embodiment. At that time, in the present embodiment, the opportunity loss calculation unit 12 corrects the opportunity loss of the target product set by subtracting the quantity in which the category demand shift occurs from the opportunity loss of the target product set.

Specifically, the opportunity loss calculation unit 12 calculates the opportunity loss in consideration of the single item demand shift by using the method shown in the first embodiment. Further, the opportunity loss calculation unit 12 includes the number of demands (that is, the first demand number) of other product sets when the products included in the target product set are not out of stock, and the target product set. Calculate the difference between the number of demands (that is, the number of second demands) of other product sets when the product is out of stock. Then, the opportunity loss calculation unit 12 corrects the difference between the number of first demands and the number of second demands by subtracting it from the opportunity loss of the target product set.

FIG. 10 is an explanatory diagram showing an example of processing for calculating a category demand shift. The product pattern illustrated in FIG. 10 is assumed to indicate the product pattern in FIG. Here, it is assumed that the product pattern of the target product set is 7.

The opportunity loss calculation unit 12 has the number of demands (8.0 pieces) of the target product set in the case of the product pattern 7 and the number of demands (9) in the case of the pattern (pattern 8) in which all the products exist in the target product set. The difference from 0.0) is calculated as 1.0. Further, the opportunity loss calculation unit 12 corresponds to the demand number of 1.1 (second demand number) of the classification β in the case of the product pattern 7 of the target product set and the pattern (pattern 8) in which all the products exist. The difference from the number of demands of 1.0 in the category β (first number of demands) is calculated as 0.1 as the category demand shift.

Then, the opportunity loss calculation unit 12 subtracts the difference (0.1 pieces) calculated based on the other product sets from the difference (1.0 pieces) calculated based on the target product set, and the opportunity loss is lost. Is corrected to 0.9.

Further, in the present embodiment, the case where there is one other product set has been described, but there may be a plurality of other product sets. In that case, the opportunity loss calculation unit 12 calculates the difference between the number of first demand and the number of second demand for each other product set, and corrects the sum of the calculated differences to be subtracted from the opportunity loss of the target product set. You may.

The opportunity loss calculation unit 12 corrects the opportunity loss only when the difference (or the sum) between the number of first demand and the number of second demand is smaller than the opportunity loss of the target product set. You may.

Further, in the present embodiment, the method of reducing the category demand shift as it is from the opportunity loss of the target product set is illustrated, but the category demand shift may be corrected as predetermined. The opportunity loss calculation unit 12 may use, for example, the value of the category demand shift standardized based on the price of the product of the target product set and the price of the product of another product set. Further, when a plurality of other product sets exist, the opportunity loss calculation unit 12 may determine whether or not to correct the category demand shift based on the constraint that the category demand shift is applied or not applied.

Hereinafter, an example of a category demand shift will be described with reference to a specific example. For example, it is assumed that there are seven types of products to be sold: rice balls, side dishes, sweet buns, sandwiches, bento boxes, pasta, and fried noodles. When the products are classified by each type, if there is a so-called cannibalization relationship between rice balls, prepared foods, sweet buns and sandwiches, the opportunity loss calculation unit 12 will use these classifications when calculating the opportunity loss of rice balls. Opportunity costs may be corrected using the category demand shifts that occur between them.

On the other hand, if there is no clear cannibalization relationship between lunch boxes, pasta and fried noodles, and rice balls, the opportunity loss calculation unit 12 will generate category demand between these categories when calculating the opportunity loss of rice balls. The shift may not be used to correct the opportunity loss.

Next, the operation of the opportunity loss calculation system of this embodiment will be described. FIG. 11 is a flowchart showing an operation example of the opportunity loss calculation system of the present embodiment. The process of calculating the opportunity loss of the target product is the same as in steps S11 and S12 of the flowchart of FIG. 7.

The opportunity loss calculation unit 12 calculates the category demand shift and corrects the opportunity loss (step S21). The correction unit 13 corrects the demand number of the target product set by using the corrected opportunity loss (step S22). After that, the process in which the learning unit 14 creates a prediction model and predicts the demand of the target product set is the same as in steps S14 and S15 of the flowchart of FIG. 7.

As described above, in the present embodiment, the opportunity loss calculation unit 12 corrects the opportunity loss by using the category demand shift. Therefore, the opportunity loss of the store as a whole can be calculated more appropriately.

Next, the outline of the present invention will be described. FIG. 12 is a block diagram showing an outline of the opportunity loss calculation system according to the present invention. The opportunity loss calculation system 80 according to the present invention is the number of demands without shortage and the number of demands when the products included in the target product set are not out of stock for each target product set including a plurality of products. A storage unit 81 (for example, a storage unit 11) that stores the number of out-of-stock demands, which is the number of demands when one or more products included in the target product set are out of stock, in association with each period. And, the opportunity loss of the target product set including the product in the period when a certain product is out of stock is calculated based on the number of demands without shortage and the number of demands with out of stock in the corresponding period stored in the storage unit 81. A loss calculation unit 82 (for example, an opportunity loss calculation unit 12) is provided.

With such a configuration, the opportunity loss of the store as a whole can be calculated more appropriately.

Specifically, the opportunity loss calculation unit 82 may calculate the difference between the number of demands with shortages and the number of demands without shortages as the opportunity loss of the target product set.

Further, the storage unit 81 may store the number of shortages and demands for each period according to the pattern of shortages of the products included in the target product set. Then, the opportunity loss calculation unit 82 has the number of demands without shortages stored in the storage unit 81 during the period for calculating the opportunity loss of the target product set, and the number of demands with shortages in the target product set in which the pattern of shortages matches. The opportunity loss may be calculated based on.

With such a configuration, it is possible to calculate the opportunity loss with higher accuracy according to the product shortage pattern.

In addition, the storage unit 81 contains the first demand number, which is the number of demands of other product sets when the products included in the target product set are not out of stock, and the products included in the target product set. The second demand number, which is the demand number of other product sets when the product is out of stock, may be stored in association with each other. Then, the opportunity loss calculation unit 82 may make a correction to reduce the difference between the number of first demands and the number of second demands from the opportunity loss of the target product set.

With such a configuration, the opportunity loss can be calculated in consideration of the demand shift (category demand shift) across the product set.

Further, the opportunity loss calculation system 80 includes a correction unit (for example, a correction unit 13) that corrects the sales of the product set including the product during the period when the product is out of stock based on the calculated opportunity loss. May be good. In this case, the opportunity loss calculation system 80 may include a learning unit (for example, a learning unit 14) that learns a model for predicting the number of demands of the target product set based on the corrected sales.

As an example, the target product set may be a set of products of the same type.

Some or all of the above embodiments may also be described, but not limited to:

(Appendix 1) For each target product set that includes multiple products, the number of demands without shortage, which is the number of demands when the products included in the target product set are not out of stock, and the target product set include Includes a storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more of the missing products are out of stock, in association with each period, and the product in the period when a certain product is out of stock. It is characterized by including an opportunity loss calculation unit that calculates an opportunity loss of a target product set based on the number of demands without a shortage and the number of demands with a shortage in a corresponding period stored in the storage unit. Opportunity loss calculation system.

(Appendix 2) The opportunity loss calculation unit is the opportunity loss calculation system according to Appendix 1, which calculates the difference between the number of demands with shortages and the number of demands without shortages as the opportunity loss of the target product set.

(Appendix 3) The storage unit stores the number of shortages and demands for each period according to the pattern of shortage of products included in the target product set, and the opportunity loss calculation unit stores the target product stored in the storage unit. Opportunity described in Appendix 1 or Appendix 2 to calculate the opportunity loss based on the number of demands without shortages during the period for calculating the opportunity loss of the set and the number of demands with shortages of the target product set that matches the pattern of the shortages. Loss calculation system.

(Appendix 4) The storage unit contains the first demand number, which is the number of demands of other product sets when the products included in the target product set are not out of stock, and the products included in the target product set. The number of second demands, which is the number of demands of other product sets when is out of stock, is stored in association with each other, and the opportunity loss calculation unit is the difference between the number of first demands and the number of second demands. The opportunity loss calculation system according to any one of Supplementary note 1 to Supplementary note 3, wherein the modification is made so as to reduce the opportunity loss of the target product set.

(Appendix 5) One of Appendix 1 to Appendix 4 equipped with a correction unit that corrects the sales of the product set including the product during the period when a product is out of stock based on the calculated opportunity loss. The opportunity loss calculation system described.

(Appendix 6) The opportunity loss calculation system according to Appendix 5 including a learning unit that learns a model for predicting the number of demands of a target product set based on the corrected sales.

(Appendix 7) The target product set is the opportunity loss calculation system according to any one of Supplements 1 to 6, which is a set of products of the same type.

(Appendix 8) For each target product set containing multiple products, the number of demands without shortage, which is the number of demands when the products included in the target product set are not out of stock, and the target product set include The demand for out-of-stock items corresponding to the period for calculating the opportunity loss from the storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more of the products are out of stock, in association with each period. Opportunity loss calculation, characterized in that the number and the number of demands without shortages are specified, and the opportunity loss of the target product set during the period is calculated based on the specified number of demands without shortages and the number of demands with shortages. Method.

(Appendix 9) The opportunity loss calculation method according to Appendix 8, which calculates the difference between the number of demands with shortages and the number of demands without shortages as an opportunity loss of a target product set.

(Appendix 10) The number of demands without shortage and the target product set, which is the number of demands when the products included in the target product set are not out of stock for each target product set containing a plurality of products on the computer. The above-mentioned shortage corresponding to the period for calculating the opportunity loss from the storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more of the products included in the item is out of stock, in association with each period. Calculation to calculate the opportunity loss of the target product set during the period based on the specified processing to specify the number of demands with goods and the number of demands without shortages, and the number of demands without shortages and the number of demands with shortages specified. Opportunity loss calculation program for executing processing.

(Appendix 11) The opportunity loss calculation program according to Appendix 10, which causes a computer to calculate the difference between the number of demands with shortages and the number of demands without shortages as an opportunity loss of a target product set in a calculation process.

Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above embodiments and examples. Various changes that can be understood by those skilled in the art can be made within the scope of the invention of the present application in terms of the configuration and details of the invention of the present application.

This application claims priority on the basis of Japanese Patent Application 2016-135974 filed on 8 July 2016 and incorporates all of its disclosures herein.

10 Opportunity loss calculation system 11 Storage unit 12 Opportunity loss calculation unit 13 Correction unit 14 Learning unit 15 Prediction unit 80 Opportunity loss calculation system 81 Storage unit 82 Opportunity loss calculation unit

Claims (9)

For each target product set that includes multiple products, the number of demands without shortage, which is the number of demands when the products included in the target product set are not out of stock, and the products included in the target product set. A storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more are out of stock, in association with each period.
Opportunity cost of calculating the opportunity loss of the target product set including the product in the period when the product is out of stock based on the number of demands without the shortage and the number of demands with the shortage in the corresponding period stored in the storage unit. Equipped with a loss calculation unit
The opportunity loss calculation unit calculates the difference between the number of demands with shortages and the number of demands without shortages as an opportunity loss of the target product set.
Opportunity loss calculation system characterized by this. The storage unit stores the number of out-of-stock items and demand for each period according to the pattern of out-of-stock items of the products included in the target product set.
The opportunity loss calculation unit determines the number of demands without shortages during the period for calculating the opportunity loss of the target product set stored in the storage unit and the number of demands with shortages of the target product set with the same pattern of shortages. The opportunity loss calculation system according to claim 1 , which calculates the opportunity loss based on the above. In the storage unit, the first demand number, which is the number of demands of other product sets when the products included in the target product set are not out of stock, and the products included in the target product set are out of stock. The second demand number, which is the demand number of other product sets at that time, is stored in association with each other.
The opportunity loss calculation system according to claim 1 or 2 , wherein the opportunity loss calculation unit corrects the difference between the first demand number and the second demand number from the opportunity loss of the target product set. 13 . Opportunity loss calculation system. The opportunity loss calculation system according to claim 4 , further comprising a learning unit that learns a model for predicting the number of demands of a target product set based on the corrected sales. The opportunity loss calculation system according to any one of claims 1 to 5 , wherein the target product set is a set of products of the same type. For each target product set containing multiple products , the computer is included in the target product set and the number of demands without shortage, which is the number of demands when the products included in the target product set are not out of stock. The number of out-of-stock demands corresponding to the period for calculating the opportunity loss from the storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more of the products are out of stock, in association with each period. And identify the number of demands without shortage,
An opportunity loss calculation method , wherein the computer calculates an opportunity loss of a target product set during the period from the difference between the specified number of demands without shortages and the number of demands with shortages. The opportunity loss calculation method according to claim 7 , wherein the computer calculates the difference between the number of demands with shortages and the number of demands without shortages as an opportunity loss of the target product set. On the computer
For each target product set that includes multiple products, the number of demands without shortage, which is the number of demands when the products included in the target product set are not out of stock, and the products included in the target product set The number of out-of-stock demands and the out-of-stock demand corresponding to the period for calculating the opportunity loss from the storage unit that stores the number of out-of-stock demands, which is the number of demands when one or more are out of stock, in association with each period. Specific processing to identify the number of non-product demands, and
Based on the specified number of demands without shortages and the number of demands with shortages, the calculation process for calculating the opportunity loss of the target product set during the above period is executed .
In the opportunity loss calculation process, the difference between the number of demands with shortages and the number of demands without shortages is calculated as the opportunity loss of the target product set.
Opportunity loss calculation program for.

Images