Price determination device, sales management system, price determination method and program

Abstract

When dynamically setting product prices, it will be possible to adjust the relationship between price accuracy and calculation time. [Solution] The price determination device includes a price determination means that determines the asking price of a product with a finite sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time.

Description

[Technical Field]

[0001] The present invention relates to a price determination device, a sales management system, a price determination method, and a program. [Background technology]

[0002] Dynamically setting prices can lead to increased profits. For example, the pricing device described in Patent Document 1 adjusts prices using an inventory adjustment index obtained by dividing the actual inventory quantity acquired from a POS system by the assumed inventory quantity. This adjusted price is then further adjusted by multiplying it by a depreciation rate corresponding to the remaining time, and this becomes the price for the next time period. This ensures appropriate pricing according to the actual inventory quantity, thereby improving profits and optimizing inventory to reduce waste disposal. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2003-345879 [Overview of the project] [Problems that the invention aims to solve]

[0004] As described in Patent Document 1, it is desirable to be able to dynamically set the optimal price from the perspective of profit improvement and inventory optimization, taking into account the inventory and disposal time of goods or services, demand trends, etc.

[0005] On the other hand, dynamically determining the optimal price generally requires computationally intensive methods such as dynamic programming. Such methods can take an enormous amount of time to calculate the optimal price when the scale of goods and services sales is large, and the calculation may not be completed within actual business hours.

[0006] To determine a price within a feasible computational complexity, one might consider using approximate methods rather than methods that determine the optimal price. While such approximate methods guarantee a feasible computational complexity, they often sacrifice price optimality, resulting in a trade-off between computation time and price optimality, such as obtaining a price that yields lower profits compared to the optimal price.

[0007] When dynamically setting product prices to optimize profits and inventory, it is necessary to carefully balance the trade-off between price optimization and computation time.

[0008] One example of the purpose of this disclosure is to provide a price determination device, a sales management system, a price determination method, and a program that can solve the above-mentioned problems. [Means for solving the problem]

[0009] According to a first aspect of the present invention, the price determination device includes price determination means that determines the asking price of a product with a finite sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time.

[0010] According to a second aspect of the present invention, the sales management system comprises a price determination device and a sales processing system, wherein the price determination device includes price determination means for determining the asking price of a product with a finite sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time.

[0011] According to a third aspect of the present invention, the price determination method includes a computer determining the asking price of a product with a finite sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time.

[0012] According to a fourth aspect of the present invention, the program causes a computer to determine the asking price of a product with a limited sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time. [Effects of the Invention]

[0013] According to the aspects of this disclosure, when dynamically setting the price of a product, it is possible to adjust the relationship between price optimization and calculation time. The optimality of a price, as used here, may also refer to the magnitude of the profit obtained by offering that price, or the magnitude of the profit that is expected to be obtained. The optimality of a price obtained using a certain method may also refer to the magnitude of the cumulative profit obtained, or the cumulative value of the expected profit, within the sales period when the price is offered using that method. The optimality of a price is also called the precision of the price. [Brief explanation of the drawing]

[0014] [Figure 1] This figure shows an example of the configuration of a sales management system according to at least one embodiment. [Figure 2] This figure shows an example of the configuration of a price determination device according to at least one embodiment. [Figure 3] This figure shows an example of the processing performed by a sales management system according to at least one embodiment. [Figure 4] This figure shows an example of a process in which a pre-calculation unit, according to at least one embodiment, determines feedback parameters. [Figure 5] This figure shows an example of the change in the remaining number of available items when a price determination unit according to at least one embodiment determines the offered price using a first price determination method. [Figure 6] This figure shows an example of the processing procedure performed by a price determination device according to at least one embodiment. [Figure 7] This figure shows an example of the configuration of a price determination device according to at least one embodiment. [Figure 8]This figure shows an example of the configuration of a sales management system according to at least one embodiment. [Figure 9] This figure shows an example of the processing in a price determination method according to at least one embodiment. [Figure 10] This figure shows an example of a computer configuration according to at least one embodiment. [Modes for carrying out the invention]

[0015] The embodiments will be described below with reference to the drawings. In the following, letters preceded by a tilde will be followed by " ~ Sometimes a tilde is added to represent it. For example, a D with a tilde is written as D ~ It is also written as follows:

[0016] <First Embodiment> Figure 1 is a diagram showing an example of the configuration of a sales management system according to at least one embodiment. In the configuration shown in Figure 1, the sales management system 1 comprises a price determination device 100 and a sales processing system 200.

[0017] Sales Management System 1 is a system for managing the sale of products. The price determination device 100 determines the price (offered price) of a product. In particular, the price determination device 100 can determine the price of products with a finite sales period and determines the price for each time period (time zone). The time referred to here is the date and time, that is, a time that distinguishes between different dates. The products that the price determination device 100 targets for price determination are not limited to specific items. For example, the products that the price determination device 100 targets for price determination may be goods, services, or a combination of goods and services.

[0018] The price determination device 100 may be configured using a computer such as a workstation (WS) or a personal computer (PC). Alternatively, the price determination device 100 may be configured using an AISC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0019] The sales processing system 200 performs processing for the sale of goods. In particular, the sales processing system 200 displays the price determined by the price determination device 100 and observes the demand for goods. Specifically, the sales processing system 200 observes the number of goods sold as actual demand. The sales processing system 200 transmits the demand information obtained from the observation to the price determination device 100. The sales processing system 200 may be configured using a computer system such as a client-server system. Alternatively, the sales processing system 200 may be configured using AISC or FPGA.

[0020] Regarding price presentation, the sales processing system 200 may directly present the price. For example, the sales processing system 200 may present the price when selling products online. Alternatively, the sales processing system 200 may present the price indirectly. For example, the sales processing system 200 may present the price to a store employee, who then displays the price in the store.

[0021] Regarding demand observation, the sales processing system 200 may directly count demand. For example, the sales processing system 200 may have a function to sell products, such as an online airline ticket reservation system, and record sales performance (sales results) when a sale is completed and count the number of sales. Alternatively, the sales processing system 200 may accept input of demand information. For example, the sales processing system 200 may accept input of sales performance information from store employees.

[0022] Furthermore, the sales period for a product will be represented in time steps from time 1 to time T. T is an integer representing the final time of the sales period, and T ≥ 2. One step in the time steps is also called a time or time zone. Time 1 is also referred to as the start time of sales. Time T is also referred to as the end time of sales.

[0023] The price determination device 100 determines the price at each time interval (i.e., at each time step) within the sales period. The sales processing system 200 displays the price determined by the price determination device 100 at each time interval within the sales period and observes demand. Furthermore, the time before the product goes on sale will be represented as time 0.

[0024] Each step in the time step may be set to the same length, such as one step being set to one hour. Alternatively, the length of each step may differ, such as one step being set to one hour between 8:00 AM and 8:00 PM, and the entire period (from 8:00 PM to 8:00 AM) being set to one step. Furthermore, even if the length of each step from time 1 to T is the same, the length of time 0 may be different from the length of each step from time 1 to T.

[0025] In the following, individual times may be indicated by adding a time identifier number after the "time" or "time step," such as time 0, time 1, ..., or time step 0, time step 1, .... Alternatively, individual times may be indicated by adding a time identifier number after "t=", such as t=0, t=1, ....

[0026] Figure 2 shows an example of the configuration of the price determination device 100. In the configuration shown in Figure 2, the price determination device 100 comprises a communication unit 110, a display unit 120, an operation input unit 130, a storage unit 180, and a processing unit 190. The processing unit 190 comprises a pre-calculation unit 191 and a price determination unit 192.

[0027] The communication unit 110 communicates with other devices. For example, the communication unit 110 transmits the price determined by the price determination device 100 to the sales processing system 200. The communication unit 110 also receives information on actual demand from the sales processing system 200.

[0028] The display unit 120 includes a display screen such as a liquid crystal panel or an LED (Light Emitting Diode) panel, and displays various images. For example, the display unit 120 may display various data used in price determination, such as the price schedule determined by the price determination device before the start of product sales, demand forecasts according to the price schedule, and actual demand observed by the sales processing system 200. Also, if the sales management system 1 is installed in a store and presents prices to store employees, the display unit 120 may display prices in addition to, or instead of, the sales processing system 200.

[0029] The operation input unit 130 includes, for example, input devices such as a keyboard and a mouse, and accepts user operations. For example, the operation input unit 130 may accept user operations to set various information used in determining the price, such as the initial stock quantity of the product, demand distribution, sales period, and selectable price options.

[0030] The storage unit 180 stores various data. For example, the storage unit 180 may store various data used in price determination, such as the initial inventory quantity of the product, demand distribution, sales period, configurable price options, price schedule, and demand forecast. The storage unit 180 is configured using the storage devices provided by the price determination device 100.

[0031] The processing unit 190 controls various parts of the price determination device 100 to perform various processes. The functions of the processing unit 190 are performed, for example, by the CPU (Central Processing Unit) of the price determination device 100 reading a program from the storage unit 180 and executing it. The pre-calculation unit 191 performs various calculations as pre-processing for price determination, such as calculating the price schedule and calculating demand forecasts based on the price schedule, before the product goes on sale.

[0032] The price determination unit 192 determines the price of the product at each time point within the product's sales period. The price determination unit 192 is an example of a price determination means. The price determination unit 192 changes the price determination method before or after a predetermined time. The time at which the price determination unit 192 changes the price determination method is also referred to as the method change time.

[0033] Before the method change time, the price determination unit 192 determines the price using a method that, while less accurate than the price determination method after the method change time, allows for a price to be determined in time for the price announcement with simple calculations. On the other hand, after the method change time, the price determination unit 192 determines the price using a method that performs more complex calculations to obtain a highly accurate price compared to the price determination method before the method change time.

[0034] As mentioned above, the accuracy of a price may be the magnitude of the profit obtained by offering that price, or the magnitude of the profit that is expected to be obtained. The accuracy of a price obtained using a certain method may be the magnitude of the cumulative profit obtained, or the cumulative value of the expected profit, within the sales period when the price is offered using that method. More specifically, the accuracy of a price obtained using a certain method may be the magnitude of the cumulative profit obtained, or the cumulative value of the expected profit, by the end of the sales period when the price is offered using that method until the end of the sales period.

[0035] In the following, the expected profit will also be referred to as the expected profit. The expected profit may be the expected value of the profit, but is not limited to a probabilistically calculated value. Furthermore, in the following, the cumulative value of profit will simply be referred to as profit. The cumulative value of expected profit will also simply be referred to as expected profit.

[0036] Comparing the period before and after the method change, the time until the end of sales is longer before the method change. Before the method change, there are more options for price combinations to offer at each time step until the end of sales. Therefore, it is likely that before the method change, more time is required to calculate the price that will yield the greatest profit by the end of sales.

[0037] For example, if the asking price for a certain time (a certain time step) cannot be determined by the start of that time, it is possible to offer a standard price, such as the list price, at that time. In this case, the opportunity to earn greater profits may be missed because the price offered does not reflect the situation at the time of price determination, such as the number of items in stock. In contrast, as described above, by using a method that allows the price determination unit 192 to determine the price in a calculation time that is sufficient to meet the timing of price presentation, the price determination device 100 can present the price at each time point, and it is expected that opportunities to obtain greater profits will not be missed compared to, for example, selling at a fixed price.

[0038] On the other hand, comparing the period before and after the method change, the time until the end of sales is shorter after the method change. After the method change, there are fewer options for price combinations to offer at each time step until the end of sales. Therefore, it is possible that after the method change, the time required to calculate the price that will yield the greatest profit by the end of sales is shorter. Therefore, as described above, even if the price determination unit 192 determines the price using a method that yields a highly accurate solution, the calculation time can be kept within a range that allows price presentation to be performed. As a result, the price determination device 100 can present a price at each time point, and the accuracy of the presented price is expected to be relatively high. In particular, the accuracy of the price is expected to be higher than if the price determination unit 192 were to determine the price using the same method after the method change time as it did before the method change time.

[0039] Because the price determination unit 192 has relatively high accuracy in determining the price, it is expected that a relatively large profit can be obtained. Furthermore, by determining a relatively accurate price near the end of sales, the price determination unit 192 is expected to be able to offer a price that meets demand, ensuring that all products are sold out by the end of sales, or that only a small number of products remain unsold at the end of sales. In this respect, the possibility of reduced profits due to unsold products can be mitigated.

[0040] In this way, the price determination unit 192 can adjust the relationship between price accuracy and calculation time by using different price determination methods before and after the method change time. The price determination method used by the price determination unit 192 at a time prior to the method change time is also referred to as the first price determination method. The price determination method used by the price determination unit 192 at a time later than the method change time is also referred to as the second price determination method.

[0041] The following explanation will describe, as an example, the case in which the price determination unit 192 uses a first price determination method in which it corrects the forecast value of demand by multiplying the error between the forecast value and the actual value of the remaining inventory of the product by a coefficient. The explanation will also describe, as an example, the case in which the price determination unit 192 uses a second price determination method in which it determines the price in order to maximize the expected profit (expected profit) using information on the probability distribution of demand. However, the price determination method used by the price determination unit 192 is not limited to a specific method.

[0042] Figure 3 shows an example of the processing performed by the sales management system 1. In the process shown in Figure 3, the pre-calculation unit 191 calculates the average demand function based on demand distribution information, time information, and price information. Demand distribution information is information that shows the probability distribution of demand based on price at different times. The probability distribution of demand at each time point is D t It is also written as {D t} t It is also written as follows:

[0043] {} t This represents a set containing elements for each time point. Furthermore, in the following, the period to which an element of a set belongs may be explicitly indicated. For example, a set containing elements at each time from the start time of sales (time 1) to the end time of sales (time T) is expressed as {}. t=1 T It can also be written like this.

[0044] Time information indicates the time from the start to the end of the sales period. As described above, the start time of the sales period will be represented by Time 1, and the end time of the sales period will be represented by Time T. The sales period will start at the beginning of Time 1 and end at the end of Time T. The sales management system 1 will display prices and observe demand at each time from Time 1 to Time T. Time information can also be expressed as [T]={1,···,T}.

[0045] The price information is information that indicates the price options that the price determination unit 192 can determine. Let N be the number of price options that the price determination unit 192 can determine, and these options are also denoted as p1, ..., and pN. The price determination unit 192 determines the price to be one of p1, ..., or pN at each time step. Price information can also be expressed as [P]={p1, ..., pN}. Demand distribution information, time information, and price information may be input into the price determination device 100 by the user. The user referred to here may be a person who manages the price determination device 100.

[0046] The average demand function is a function that takes time and price as input and outputs the average value in the probability distribution of demand. For example, if the demand distribution information is expressed by a function that shows the mean value and a function that shows the variance of the probability distribution, the pre-calculation unit 191 may use the function that shows the mean value as indicated in the demand distribution information as the average demand function. The average value of demand is also called average demand.

[0047] The average demand function is also denoted as λ(t,p). t represents time. p represents, as a real number, the price that is the target of demand forecasting. Further, the average demand function may be expressed as λ:Τ×R + →R + Here, Τ represents time information. R + represents the set of non-negative real numbers.

[0048] Further, the pre-calculation unit 191 determines a reference demand and a price schedule (schedule of prices) based on the average demand function, time information, price information, and an initial inventory quantity, and calculates a reference inventory quantity. The initial inventory quantity is the inventory quantity of the product before the start of sales. The initial inventory quantity is also denoted as n0.

[0049] The price schedule is a time series of prices provisionally determined as offered prices from the sales start time to the sales end time. The price provisionally determined as the offered price at time t is also referred to as a reference price, and is also denoted as p t,0 The price schedule is also denoted as {p t,0} t

[0050] The reference demand is the demand assumed for each time when the pre-calculation unit 191 determines the price schedule. The pre-calculation unit 191 calculates the reference demand as a value (not as a probability distribution). The reference demand at time t is also denoted as λ t,0 The set of reference demands for each time is also denoted as {λ t,0} t

[0051] The pre-calculation unit 191 determines the price schedule and reference demand from the sales start time to the sales end time by solving an optimization problem. The evaluation function in the optimization problem solved by the pre-calculation unit 191 to determine the price schedule and reference demand is expressed as shown in Formula (1).

[0052] [Formula]​​

[0053] λ t This indicates the demand at time t. p(t,λ t ) is when the demand at time t is λ t This shows the price such that the average demand function λ(t,p) is fixed at time t. t If the inverse function of (p) can be found, then that inverse function is the function p(t,λ t ) It may also be used as such.

[0054] λ t p(t,λ t ) is the demand at time t = λ t The predicted profit at time t is shown. Here, it is assumed that all sales revenue can be considered as profit. Σ t=1 T λ t p(t,λ t ) The prices offered at each time from the start time of sales (t=1) to the end time of sales (t=T) are p1, ..., p T This then shows the cumulative value of the predicted profit during the sales period.

[0055] The pre-calculation unit 191 calculates the demand λ at each time from time t=1 to t=T such that the value of the evaluation function shown in equation (1) is as large as possible. t The set {λ} t} t=1 T We search for a solution and obtain the set {λ t} t=1 T The reference demand λ t,0 The set {λ} t,0} t=1 T This is adopted as follows: The pre-calculation unit 191 selects a set of reference demand {λ} that maximizes the cumulative value of the predicted profit during the sales period. t,0} t=1 T This can be understood as searching for a solution.

[0056] The first constraint in the optimization problem that the pre-calculation unit 191 solves to determine the price schedule and reference demand is given by equation (2).

[0057]

number

[0058] Equation (2) shows the demand λ at each time from time t=1 to t=T. t The cumulative value Σ t=1 T λ t This sets a constraint that the initial inventory quantity is less than or equal to n0. This constraint indicates that the number of items that can be sold within the sales period is less than or equal to the initial inventory quantity n0.

[0059] The second constraint in the optimization problem that the pre-calculation unit 191 solves to determine the price schedule and reference demand is given by equation (3).

[0060]

number

[0061] Equation (3) is provided to limit the range of solution search performed by the pre-calculation unit 191 to a finite range. The constraint conditions shown in Equation (3) are set for each time from time t=1 to t=T. λ max,t λ represents the maximum expected demand at time t. max,t This may be set to the initial inventory quantity n0.

[0062] The pre-calculation unit 191 calculates the set of reference demands {λ} by searching for a solution in the optimization problem. t,0} t=1 T When you obtain the reference demand λ t,0 Calculate the price that will yield the desired result, and set the price schedule {p t,0} t It will be adopted as follows: The pre-calculation unit 191 calculates the reference demand λ obtained in the solution search.t,0 The function p(t,λ) t Enter the reference price p t,0 You may also calculate it in this way. The price schedule from time t=1 to t=T is {p t,0} t=1 T It is also written as follows:

[0063] Set of reference demands {λ t,0} t=1 T and price schedule {p t,0} t=1 T This combination can be seen as a plan predetermined by the pre-calculation unit 191 to maximize the profit obtained under the assumption that demand does not fluctuate probabilistically. Here, "predetermined" means before the start of the sales period. In the optimization problem shown by equations (1) to (3), demand λ t It is expressed as a value (rather than a probability distribution). The evaluation function shown in equation (1) is an example of an evaluation function in which demand is expressed as a value.

[0064] Solving the optimization problem shown in equations (1) through (3) can be understood as calculating a plan that maximizes the profit obtained (cumulative profit over the sales period) (i.e., a plan that maximizes the profit obtained) using demand, which is expressed as a value. Reference demand is an example of a predicted demand value obtained by solving an optimization problem using an evaluation function (shown in equation (1)) that indicates the expected profit during the sales period, before the start of the sales period.

[0065] The reference inventory quantity is a predicted value of the inventory quantity calculated based on reference demand. The pre-calculation unit 191 calculates the reference inventory quantity n for each time from time t=1 to t=T. t,0 This is calculated based on equation (4).

[0066]

number

[0067] Here, the reference inventory quantity at the end of time t is defined as the reference inventory quantity n at time t. t,0 Equation (4) is given by the reference stock quantity n at time t. t,0 The reference demand λ from time τ=1 to τ=t is calculated from the initial inventory n0. τ,0 This indicates that it is calculated by subtracting the cumulative value (i.e., the predicted number of items sold from time τ=1 to τ=t).

[0068] Furthermore, the pre-calculation unit 191 determines a price determination policy (a function for determining the price) based on demand distribution information, time information, price information, and initial inventory. The pre-calculation unit 191 calculates the value function V shown in equation (5). * We solve the optimization problem using inversely from time t=T to t=T-T0+1, and determine the price policy π * Obtain it.

[0069]

number

[0070] Time t = T - T0 indicates the time of the method change. Price determination policy π * This is a function for the price determination unit 192 to determine the price using the second price determination method. The price determination unit 192 determines the price using the first price determination method from time t=1 to time t=T-T0, and then determines the price using the second price determination method from time t=T-T0+1 to time t=T.

[0071] π represents the price determination policy. The price determination policy π is a function that takes the initial inventory quantity n0 and time t as inputs and outputs the price p. The price determination policy π can be expressed as π:[n0]×T→P. [n0] represents the set of integer values ​​from 0 to n0, i.e., [n0]={0,1,2,···,n0}. As mentioned above, T represents time information (set {1,···,T}). P represents price information (set {p1,···,pN}). Here, the initial inventory quantity n0 is the price determination policy π* It may be the inventory quantity at the start of the period for which the price is determined using this.

[0072] Π represents the set of pricing strategies π. The pre-calculation unit 191 searches the set Π as the search space to obtain the value function V * as a solution that maximizes the value as much as possible (that is, the value function V * a solution that maximizes the value of ) as the pricing strategy π * to obtain.

[0073] Under the pricing strategy π, the average demand function λ(t,p) can be expressed as λ(t,p)=E[D t |P t =p]. E[] represents the expected value following the probability distribution (demand distribution). E[D t |P t =p] represents, under the pricing strategy π, the price P at time t t the demand distribution D when the price is p t represents the expected value of demand under this distribution.

[0074] E π [Σ τ=T-t+1 T p τ D ~ τ represents the expected value of the cumulative profit obtained under the pricing strategy π from time t=T-t+1 to time t=T. D ~ t =min(D t ,n t-1 ) represents the quantity actually sold at time t. sup π∈Π E π [Σ τ=T-t+1 T p τ D ~ τ represents E under π∈Π π [Σ τ=T-1+1 T p τ D ~ τ indicates the maximum value of .

[0075] The pre-calculation unit 191 is E π [Σ t=1 T p t D ~ t The price determination policy π that maximizes the value of ] is the price determination policy π as the solution to the optimization problem. * They will be hired as such. In the second price determination method, the price determination unit 192 sets the actual remaining inventory at the start of the period in which it wants to maximize the expected value of cumulative profit as the initial inventory for that period and sets the price determination policy π * The input is then entered into the price determination unit 192. The price determination unit 192 also determines the start time of the period for which it wants to maximize the expected value of cumulative profit using the price determination policy π. * Enter it here.

[0076] The pre-calculation unit 191 may also be configured to solve the optimization problem in reverse using dynamic programming. In this case, the inventory quantity n t-1 Regardless of the optimal value function V at times t and t+1, * Assume that equation (6) holds between them.

[0077]

number

[0078] Using equation (6) for t=T, V for any inventory amount n * Since (n, T+1) = 0, V * (n T-1 ,T) is found. Then, at each time step t, in the order t=T-1,...,1, and an arbitrary inventory amount n at each time step, the inventory amount n is determined. t-1 For ∈{0,1,2,···,n0}, V * (n T-1 t) can be found. Also, any inventory quantity n at each time point t t-1 For ∈{0,1,2,···,n0}, V * (n T-1In the process of finding t), we find the λ that maximizes the expected value of the right-hand side of equation (6). That is, we find the price that maximizes the expected value of the right-hand side of equation (6), and thus we can find the optimization policy π * :[n0]×[T]→[P] is obtained.

[0079] Solving the optimization problem using the value function shown in equation (5) to determine a price determination policy can be understood as calculating a price determination policy that maximizes the profit obtained (i.e., a price determination policy that yields the largest possible profit) using demand represented by a probability distribution. Price determination policy π * This is an example of a function obtained by solving an optimization problem using an evaluation function that shows the expected value of the cumulative profit to be obtained during the period in which the second price determination method is used, before the start of the sales period.

[0080] Furthermore, the pre-calculation unit 191 calculates the value function V * The feedback parameters are determined using this method. The feedback parameter is a coefficient used by the price determination unit 192 to adjust the price according to the remaining inventory using the first price determination method. The feedback parameter at time t is a t It is also written as follows: time-dependent feedback parameter a t The set of {a t} t It is also written as follows: The price determination unit 192 uses feedback parameter a t Using this, we can determine the expected demand λ for time t. t This is calculated as shown in equation (7).

[0081]

number

[0082] In equation (7), λ t is the feedback parameter a t The adjusted demand at time t is shown using [a specific method / framework]. The adjusted demand is also called assumed demand. Then, the price determination unit 192 calculates the assumed demand λ t The function p(t,λ) t ) Input the expected demand λ t The proposed price p t Calculate.

[0083] Figure 4 shows an example of the process by which the pre-calculation unit 191 determines the feedback parameters. Value function V * V is a discrete function of inventory, and the pre-calculation unit 191 approximates it with a continuous function. The pre-calculation unit 191 calculates the value function V * The method of approximating the value function is not limited to any particular method, as long as the convexity of the value function is preserved.

[0084] Then, the pre-calculation unit 191 calculates the continuous value function V * The second derivative of d 2 V * / dx 2 Calculate the derivative with respect to the inventory quantity. dx represents the derivative with respect to the inventory quantity. Furthermore, the pre-calculation unit 191 calculates the second derivative of the average return. Then, the pre-calculation unit 191 solves the recurrence relation shown in equation (8) to obtain the set of feedback parameters {a t} t=2 T-T0 To decide.

[0085]

number

[0086] The pre-calculation unit 191 solves the recurrence relation shown in equation (8), which solves the optimization problem shown in equation (9), and calculates the evaluation function Rev(σ²,···,σ T-T0+1 σ²,···,σ that maximizes the value of ) T-T0+1 , and a2,···,a T-T0+1 This is equivalent to finding [something].

[0087]

number

[0088] v t This shows the distribution of demand at time t. Evaluation function Rev(σ2,···,σ T-T0+1 This is the difference between the expected profit obtained when adjusting the price with feedback and the expected profit obtained when no price adjustment is made without feedback. Here, the expected profit is the expected value of the cumulative profit obtained from time t=1 to t=T. Therefore, solving the recurrence relation shown in equation (8) to determine the feedback parameters can be understood as solving the equation that maximizes the expected value of the cumulative profit obtained during the sales period to calculate the feedback parameters. Feedback parameters are examples of coefficients calculated by solving the equation (equation (8)) that maximizes the expected profit obtained during the sales period.

[0089] Furthermore, in the process shown in Figure 3, the price determination unit 192 calculates the actual remaining inventory (actual remaining inventory) based on the actual demand observed by the sales processing system 200 and the initial inventory quantity. The actual demand at time t is d t It is also written as follows:

[0090] For example, at time 1, the price determination unit 192 subtracts the actual demand d1 at time 1 from the initial inventory n0 to calculate the actual remaining inventory n1 at time 1 as n1 = n0 - d1. Furthermore, at time t from time 2 to time T-T0, the price determination unit 192 determines the actual remaining inventory n at time t-1. t-1 From the actual demand d at time t t Subtracting this, we get the actual remaining inventory n at time t. t to n t =max(n t-1 -d t Calculate as ,0).

[0091] Furthermore, the price determination unit 192 determines the quoted price. At each time from time 1 to time T-T0, the price determination unit 192 determines the quoted price using the first price determination method. In the first price determination method, the price determination unit 192 adjusts the assumed demand according to the error between the remaining inventory and the reference inventory. As described above, the price determination unit 192 adjusts the demand based on equation (7). Then, the price determination unit 192 calculates the assumed demand λ t The function p(t,λ) t ) Input the expected demand λ t The proposed price p t Calculate.

[0092] Here, the pre-calculation unit 191 calculates the feedback parameter a t to, a t The calculation is performed to obtain a value such that n is ≥ 0. t-1 -n t-1,0 If >0, i.e., the actual remaining inventory number n t-1 This refers to the remaining stock quantity n t-1,0 If it is more than a t (n t-1 -n t-1,0 )≧0, and the price determination unit 192 determines the assumed demand λ t The reference demand λ t,0 The above values ​​are determined. In this case, the price determination unit 192 is the assumed demand λ t Price p t Determining the actual remaining inventory number n t-1 However, the reference remaining inventory number n in the original plan t-1,0 Since there is a surplus, this can be interpreted as setting prices to increase demand beyond the initial plan.

[0093] On the other hand, n t-1 -n t-1,0 If <0, i.e., the actual remaining inventory number n t-1 This refers to the remaining stock quantity n. t-1,0 If less than a t (n t-1 -n t-1,0 )≦0, and the price determination unit 192 determines the assumed demand λ t The reference demand λ t,0 The following values ​​will be determined. In this case, the price determination unit 192 is the assumed demand λ t Price p t Determining the actual remaining inventory number n t-1 However, the reference remaining inventory number n in the original plan t-1,0 Since there is a shortage, this can be interpreted as setting prices to reduce demand compared to the original plan.

[0094] On the other hand, at each time from time T-T0+1 to time T, the price determination unit 192 determines the quoted price using the second price determination method. In the second price determination method, the price determination unit 192 determines the price determination policy π * (n,t) is the actual remaining inventory at time t-1 n t-1 Enter the time t and the price p t Calculate.

[0095] The price determination unit 192 determines the price p t This is transmitted to the sales processing system 200 via the communication unit 110. The sales processing system 200 uses the price p determined by the price determination unit 192. t Present actual demand d t The sales processing system 200 observes the observed actual demand d. t This is transmitted to the price determination device 100.

[0096] Figure 5 shows an example of the change in the remaining number of items when the price determination unit 192 determines the quoted price using the first price determination method. In the example in Figure 5, the initial inventory quantity is n0 = 20. Furthermore, the pre-calculation unit 191 calculates the reference price p t,0 to, p 1,0 =1000, p 2,0 =1500, p 3,0 It has been decided that it will be =2000. Furthermore, the pre-calculation unit 191 calculates the reference inventory number n t,0 n 1,0 =18, n 2,0 =14, n 3,0 The answer has been determined to be 11. Furthermore, the pre-calculation unit 191 calculates the feedback parameter a t The values ​​a2=0.3 and a3=0.2 have been determined.

[0097] At time 1, the price determination unit 192 determines the reference price p 1,0 We are using 1000 as the quoted price p1. Based on the offered price, the actual demand is d1=3, and the actual remaining inventory is n1=20-3=17.

[0098] At time t=2, the price determination unit 192 determines a2(n1-n 1,0 The calculation is p2 = 1600, where p2 = 0.3 = (17-18) = -0.3. Here, n1-n 1,0 =17-18=-1, meaning the actual remaining inventory is less than the reference inventory. Accordingly, the price determination unit 192 sets the quoted price p2 to the reference price p 2,0 It has been decided that the value is 1600, which is higher than 1500. Based on the offered price, the actual demand is d2=2, and the actual remaining inventory is n2=17-2=15.

[0099] The price determination unit 192 selects one of the price options p1, p2, ..., pN as the price p t It may also be adopted as such. For example, the price determination unit 192 selects from the options of the offered price the function p(t,λ t Alternatively, you can select the price that is closest to the price calculated using ). Alternatively, the price determination unit 192 may also be able to present prices other than the offered price options. For example, the price determination unit 192 may be able to present a function p(t,λ t The price calculated using ) and rounded to the nearest tenth may be used as the asking price.

[0100] At time t=3, the price determination unit 192 determines a3(n2-n 2,0 The calculation is (15-14) = 0.2, and the asking price is set to p3 = 1900. Here, n²-n 2,0 =15-14=1, meaning the actual remaining inventory is greater than the reference inventory. Accordingly, the price determination unit 192 sets the quoted price p3 to the reference price p 3,0 It has been decided that it will be 1900, which is cheaper than 2000.

[0101] Based on the offered price, the actual demand is d3=4, and the actual remaining inventory is n3=25-4=11. Here, the actual remaining inventory n3=11 is equal to the reference inventory n 3,0 This is the same value as =11.

[0102] In this way, the price determination unit 192 adjusts the offered price to bring the actual remaining inventory closer to the reference inventory quantity initially planned, allowing the price determination device 100 to determine the offered price in a state close to the initial plan that maximizes profits. In this respect, the price determination device 100 can determine a highly accurate offered price, and it is expected that large profits can be obtained.

[0103] Figure 6 shows an example of the processing steps performed by the price determination device 100. In the process shown in Figure 6, the price determination device 100 acquires demand distribution information, time information, price information, and initial inventory quantity (step S101). Next, the pre-calculation unit 191 determines the reference demand and the price schedule, which is a set of time periods and the prices offered at those times during the sales period, and calculates the reference inventory (step S102).

[0104] Next, the pre-calculation unit 191 determines the price determination policy and feedback parameters (step S103). Next, the processing unit 190 sets the time to t=1 (step S104). Next, the processing unit 190 determines whether the time t is less than or equal to the end-of-sale time T (step S105).

[0105] If it is determined that time t is less than or equal to the end of sales time T (step S105: YES), the processing unit 190 determines whether time t is less than or equal to the method change time T-T0 (step S106). If the processing unit 190 determines that time t is less than or equal to the method change time T-T0 (step S106: YES), the price determination unit 192 determines the price using the feedback parameters (step S111).

[0106] Next, the price determination device 100 acquires the actual demand observed by the sales processing system 200 (step S131). Next, the price determination unit 192 calculates the actual remaining inventory (step S132). Next, the processing unit 190 advances the time by one step (step S133). Specifically, the processing unit 190 increments the counter value at time t by 1. After step S133, the process returns to step S105.

[0107] On the other hand, if the processing unit 190 determines in step S106 that time t is greater than the method change time T-T0 (step S106: NO), the price determination unit 192 determines the price using the price determination policy (step S121). After step S121, the process proceeds to step S131.

[0108] On the other hand, if the processing unit 190 determines in step S105 that time t is greater than the end-of-sale time T (step S105: NO), the price determination device 100 terminates the process shown in Figure 6.

[0109] As described above, the price determination unit 192 determines the asking price of a product with a finite sales period using the first price determination method before a predetermined method change time, and using the second price determination method after the method change time. According to the price determination device 100, when dynamically setting the price of a product, the price determination method can be changed before and after the method change time to adjust the relationship between price accuracy and calculation time.

[0110] For example, as mentioned above, comparing the period before and after the method change, the period until the end of sales is longer before the method change. Before the method change, there are more options for price combinations to offer at each time step until the end of sales. Therefore, it is conceivable that before the method change, more time is required to calculate the price that will yield the greatest profit by the end of sales.

[0111] If the asking price for a given time (a given time step) cannot be determined by the start of that time, for example, a standard price such as the list price may be offered at that time. In this case, the opportunity to earn greater profits may be missed because the price offered does not reflect the situation at the time of price determination, such as the number of items in stock.

[0112] In contrast, the price determination unit 192 can determine the price using a method that, while less precise than the price determination method after the method change, allows for a simpler calculation to determine the price in time for the price announcement. This enables the price determination device 100 to present prices at each time, and it is expected that the product will be sold in a timely manner. For example, it is expected that opportunities to earn greater profits will not be missed compared to selling at a fixed price.

[0113] On the other hand, comparing the period before and after the method change, the period until the end of sales is shorter after the method change. After the method change, there are fewer options for price combinations to present at each time step until the end of sales. Therefore, it is conceivable that the time required to calculate a price that maximizes the profit obtained by the end of sales is shorter after the method change. From this, it is expected that even if the price determination unit 192 determines the price using a method that yields a more accurate solution compared to the price determination method before the method change, the calculation time can be kept within a range that makes price presentation feasible.

[0114] Therefore, the price determination unit 192 can determine the price using a method that performs more complex calculations compared to the price determination method before the method change time, thereby obtaining a highly accurate price. As a result, the price determination device 100 can present a price at each time point, and it is expected that the accuracy of the presented price will be relatively high. In particular, it is expected that the price accuracy will be higher than if the price determination unit 192 were to determine the price after the method change time using the same method as before the method change time.

[0115] Furthermore, in the first price determination method, the price determination unit 192 uses a value obtained by multiplying the error between the actual remaining inventory and the reference inventory (which is the predetermined remaining inventory) by a predetermined coefficient to adjust the demand expected in the next time step, and determines the quoted price according to the adjusted demand.

[0116] The price determination device 100 can adjust demand to approach a predetermined remaining inventory level. This allows the price determination device 100 to offer a predetermined price (price schedule) or a price close to it that maximizes the cumulative expected profit. In this respect, the price determination device 100 is expected to generate significant profits.

[0117] Furthermore, the predetermined remaining inventory quantity (reference inventory quantity) is calculated based on the reference demand, which is a forecast value of demand obtained by solving an optimization problem using an evaluation function that shows the cumulative value of profits expected during the sales period, before the start of the sales period. In the first price determination method, the price determination unit 192 calculates the adjusted demand by adding a value obtained by multiplying the error by a coefficient (feedback parameter) to the reference demand.

[0118] According to the price determination device 100, the quoted price can be determined so that the actual remaining inventory number approaches the reference inventory number. According to the price determination device 100, in this respect, it is expected that the final remaining inventory number (actual remaining inventory number after the end of the sales period) will be 0 or a small number (a small remaining inventory number), and it is expected that the waste of unsold goods can be avoided or mitigated.

[0119] Furthermore, reference demand is calculated based on the time step and the price, expressed as a real value, to maximize the cumulative value of the expected profit during the sales period. According to the price determination device 100, using prices expressed as real values ​​is expected to simplify calculations compared to using prices expressed as integer values.

[0120] Furthermore, reference demand can be obtained by solving an optimization problem using an evaluation function in which demand is expressed as a value. According to the price determination device 100, since it solves an optimization problem using an evaluation function in which demand is expressed as a value, the computational complexity of the reference price is relatively small, and it is expected that the reference price can be calculated in a relatively short time. For example, it is expected that the price determination device 100 can calculate the reference price with less computational complexity and in a shorter time than when solving an optimization problem using an evaluation function in which demand is expressed as a probability distribution.

[0121] Furthermore, the above coefficients (feedback parameters) are calculated by solving an equation that maximizes the cumulative value of the expected profit during the period in which the price determination unit 192 uses the first price determination method. According to the price determination device 100, it is expected that greater profits will be obtained than if no adjustments were made to demand.

[0122] Furthermore, the price determination unit 192 calculates the quoted price by inputting the actual remaining inventory and the time step into a price determination policy, which is a function obtained by solving an optimization problem before the start of the sales period. This policy uses a function that outputs a quoted price upon input of the inventory quantity and time step in the second price determination method, and an evaluation function that shows the cumulative value of expected profit during the period in which the second price determination method is used.

[0123] According to the price determination device 100, the second price determination method is expected to yield a relatively large profit because it determines the price determination policy by solving an optimization problem using an evaluation function that shows the cumulative value of expected profits. For example, it is expected to yield a larger profit than if the price determination device 100 were to determine the price using the first price determination method even after the method change time.

[0124] Furthermore, the price determination strategy is predetermined using demand distribution information that shows the probability distribution of demand corresponding to the offered price at each time step. According to the price determination device 100, since the price determination policy is determined based on the probability distribution of demand, it is expected that the profits obtained from price determination using the price determination policy will be large.

[0125] Furthermore, the price determination policy can be obtained by solving an optimization problem using an evaluation function in which demand is represented by a probability distribution. According to the price determination device 100, the second price determination method is expected to yield relatively large profits because it determines the price determination policy by solving an optimization problem using an evaluation function in which demand is represented by a probability distribution. For example, the price determination device 100 is expected to yield larger profits than when it solves an optimization problem using an evaluation function in which demand is represented by a value. <Second Embodiment> Figure 7 shows an example of the configuration of a price determination device according to at least one embodiment. In the configuration shown in Figure 7, the price determination device 610 includes a price determination unit 611. In this configuration, the price determination unit 611 determines the asking price of a product with a limited sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time. The price determination unit 611 is an example of a price determination means.

[0126] According to the price determination device 610, when dynamically setting the price of a product, the price determination method can be changed before and after the method change time to adjust the relationship between price accuracy and calculation time.

[0127] Comparing the period before and after the method change, the time until the end of sales is longer before the method change. Before the method change, there are more options for price combinations to offer at each time step until the end of sales. Therefore, it is likely that before the method change, more time is required to calculate the price that will yield the greatest profit by the end of sales.

[0128] For example, if the asking price for a certain time (a certain time step) cannot be determined by the start of that time, it is possible to offer a standard price, such as the list price, at that time. In this case, the opportunity to earn greater profits may be missed because the price offered does not reflect the situation at the time of price determination, such as the number of items in stock.

[0129] In contrast, the price determination unit 611 can determine the price using a method that, while less precise than the price determination method after the method change, allows for a simpler calculation to ensure the price is presented in time. This enables the price determination device 610 to present prices at each given time, and is expected to avoid missing opportunities to earn greater profits compared to, for example, selling at a fixed price.

[0130] On the other hand, comparing the period before and after the method change, the period until the end of sales is shorter after the method change. After the method change, there are fewer options for price combinations to present at each time step until the end of sales. For this reason, it is conceivable that the time required to calculate a price that maximizes the profit obtained by the end of sales is shorter after the method change. Therefore, even if the price determination unit 611 determines the price using a method that yields a more accurate solution compared to the price determination method before the method change, it is expected that the calculation time can be kept within a range that makes price presentation feasible.

[0131] Therefore, the price determination unit 611 can determine the price using a method that performs more complex calculations compared to the price determination method before the method change time, thereby obtaining a highly accurate price. As a result, the price determination device 610 can present a price at each time point, and it is expected that the accuracy of the presented price will be relatively high. In particular, it is expected that the price accuracy will be higher than if the price determination unit 611 were to determine the price after the method change time using the same method as before the method change time.

[0132] The price determination unit 611 can be implemented using, for example, the functions of the price determination unit 192 shown in Figure 2.

[0133] <Third Embodiment> Figure 8 shows an example of the configuration of a sales management system according to at least one embodiment. In the configuration shown in Figure 8, the sales management system 620 comprises a price determination device 621 and a sales processing system 623. The price determination device 621 comprises a price determination unit 622. In this configuration, the price determination unit 622 determines the asking price of a product with a finite sales period using the first price determination method before a predetermined method change time, and using the second price determination method after the method change time. The price determination unit 622 is an example of a price determination means.

[0134] According to the price determination device 621, when dynamically setting the price of a product, the price determination method can be changed before and after the method change time to adjust the relationship between price accuracy and calculation time.

[0135] Comparing the period before and after the method change, the time until the end of sales is longer before the method change. Before the method change, there are more options for price combinations to offer at each time step until the end of sales. Therefore, it is likely that before the method change, more time is required to calculate the price that will yield the greatest profit by the end of sales.

[0136] For example, if the asking price for a certain time (a certain time step) cannot be determined by the start of that time, it is possible to offer a standard price, such as the list price, at that time. In this case, the opportunity to earn greater profits may be missed because the price offered does not reflect the situation at the time of price determination, such as the number of items in stock.

[0137] In contrast, the price determination unit 622 can determine the price using a method that, while less precise than the price determination method after the method change, allows for a simpler calculation to ensure the price is presented in time. This enables the price determination device 610 to present prices at each given time, and is expected to avoid missing opportunities to earn greater profits compared to, for example, selling at a fixed price.

[0138] On the other hand, comparing the period before and after the method change, the period until the end of sales is shorter after the method change. After the method change, there are fewer options for price combinations to present at each time step until the end of sales. For this reason, it is conceivable that the time required to calculate a price that maximizes the profit obtained by the end of sales is shorter after the method change. Therefore, even if the price determination unit 611 determines the price using a method that yields a more accurate solution compared to the price determination method before the method change, it is expected that the calculation time can be kept within a range that makes price presentation feasible.

[0139] Therefore, the price determination unit 611 can determine the price using a method that performs more complex calculations compared to the price determination method before the method change time, thereby obtaining a highly accurate price. As a result, the sales management system 620 can present prices at each time, and it is expected that the accuracy of the presented prices will be relatively high. In particular, it is expected that the price accuracy will be higher than if the price determination unit 622 were to determine the price after the method change time using the same method as before the method change time.

[0140] The price determination unit 622 can be implemented, for example, using functions such as the price determination unit 192 shown in Figure 2.

[0141] <Fourth Embodiment> Figure 9 shows an example of the process in a price determination method according to at least one embodiment. The price determination method shown in Figure 9 includes determining the price (step S611). In determining the price (step S611), the computer determines the asking price of a product with a finite sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time.

[0142] According to the pricing method shown in Figure 9, when dynamically setting the price of a product, the pricing method can be changed before and after the method change time to adjust the relationship between price accuracy and calculation time.

[0143] Comparing the period before and after the method change, the time until the end of sales is longer before the method change. Before the method change, there are more options for price combinations to offer at each time step until the end of sales. Therefore, it is likely that before the method change, more time is required to calculate the price that will yield the greatest profit by the end of sales.

[0144] For example, if the asking price for a certain time (a certain time step) cannot be determined by the start of that time, it is possible to offer a standard price, such as the list price, at that time. In this case, the opportunity to earn greater profits may be missed because the price offered does not reflect the situation at the time of price determination, such as the number of items in stock.

[0145] In contrast, according to the pricing method shown in Figure 9, at the time before the method change, the price can be determined using a method that, while less precise than the pricing method after the method change, allows for a simpler calculation to ensure the price is ready in time for the price announcement. As a result, according to the pricing method shown in Figure 9, it is possible to present prices at each time, and it is expected that opportunities to earn greater profits will not be missed compared to, for example, selling at a fixed price.

[0146] On the other hand, comparing the period before and after the method change, the time until the end of sales is shorter after the method change. After the method change, there are fewer options for price combinations to offer at each time step until the end of sales. Therefore, it is conceivable that the time required to calculate a price that maximizes the profit obtained by the end of sales is shorter after the method change. From this, it is expected that even if a method that yields a more accurate solution is used to determine the price compared to the price determination method before the method change, the calculation time can be kept within a feasible range for price offering.

[0147] Therefore, according to the price determination method shown in Figure 9, it is possible to determine the price using a method that performs more complex calculations and obtains a highly accurate price compared to the price determination method before the method change time. As a result, according to the price determination method shown in Figure 9, it is possible to present a price for each time period, and it is expected that the accuracy of the presented price will be relatively high. In particular, it is expected that the price accuracy will be higher than if the price determination unit 611 were to determine the price after the method change time using the same method as before the method change time.

[0148] Figure 10 shows an example of a computer configuration according to at least one embodiment. In the configuration shown in Figure 10, the computer 700 comprises a CPU 710, a main memory 720, an auxiliary memory 730, an interface 740, and a non-volatile recording medium 750.

[0149] One or more of the above-mentioned price determination device 100, sales processing system 200, price determination device 610, price determination device 621, and sales processing system 623, or a part thereof, may be implemented in the computer 700. In that case, the operation of each of the above-mentioned processing units is stored in the auxiliary storage device 730 in the form of a program. The CPU 710 reads the program from the auxiliary storage device 730, expands it in the main memory device 720, and executes the above-mentioned processing according to the program. The CPU 710 also reserves memory areas in the main memory device 720 corresponding to each of the above-mentioned storage units according to the program. Communication between each device and other devices is performed by the interface 740 having a communication function and performing communication according to the control of the CPU 710. The interface 740 also has a port for the non-volatile recording medium 750 and reads information from the non-volatile recording medium 750 and writes information to the non-volatile recording medium 750.

[0150] When the price determination device 100 is implemented in a computer 700, the operation of the processing unit 190 and each of its parts is stored in auxiliary storage device 730 in the form of a program. The CPU 710 reads the program from the auxiliary storage device 730, loads it into the main memory 720, and executes the above processing according to the program.

[0151] Furthermore, the CPU 710 reserves a memory area for the memory unit 180 in the main memory 720 according to the program. Communication with other devices by the communication unit 110 is performed by the interface 740 having a communication function and operating under the control of the CPU 710. Display of images by the display unit 120 is performed by the interface 740 having a display device and displaying various images under the control of the CPU 710. Acceptance of user operations by the operation input unit 130 is performed by the interface 740 having an input device and accepting user operations under the control of the CPU 710.

[0152] When the sales processing system 200 is implemented on the computer 700, its operation is stored in auxiliary storage device 730 in the form of a program. The CPU 710 reads the program from auxiliary storage device 730, loads it into main memory 720, and executes the above processing according to the program.

[0153] Furthermore, the CPU 710 reserves memory in the main memory 720 for the sales processing system 200 to process, according to the program. Communication between the sales processing system 200 and other devices is performed by the interface 740, which has communication functions and operates under the control of the CPU 710. Interaction between the sales processing system 200 and the user is performed by the interface 740, which has input and output devices, presenting information to the user via the output device and accepting user operations via the input device, under the control of the CPU 710.

[0154] When the price determination device 610 is implemented in the computer 700, the operation of the price determination unit 611 is stored in auxiliary storage device 730 in the form of a program. The CPU 710 reads the program from the auxiliary storage device 730, loads it into the main memory 720, and executes the above process according to the program.

[0155] Furthermore, the CPU 710 reserves memory in the main memory 720 for the price determination device 610 to process according to the program. Communication between the price determination device 610 and other devices is performed by the interface 740 having a communication function and operating under the control of the CPU 710. Interaction between the price determination device 610 and the user is performed by the interface 740 having input and output devices, presenting information to the user via the output device and accepting user operations via the input device under the control of the CPU 710.

[0156] When the price determination device 621 is implemented in the computer 700, the operation of the price determination unit 622 is stored in auxiliary storage device 730 in the form of a program. The CPU 710 reads the program from the auxiliary storage device 730, loads it into the main memory 720, and executes the above process according to the program.

[0157] Furthermore, the CPU 710 reserves memory in the main memory 720 for processing by the price determination device 621 according to the program. Communication between the price determination device 621 and other devices is performed by the interface 740 having a communication function and operating under the control of the CPU 710. Interaction between the price determination device 621 and the user is performed by the interface 740 having input and output devices, presenting information to the user via the output device and accepting user operations via the input device under the control of the CPU 710.

[0158] When the sales processing system 623 is implemented in the computer 700, its operation is stored in auxiliary storage device 730 in the form of a program. The CPU 710 reads the program from auxiliary storage device 730, loads it into main memory 720, and executes the above processing according to the program.

[0159] Furthermore, the CPU 710 reserves memory in the main memory 720 for the sales processing system 623 to process, according to the program. Communication between the sales processing system 623 and other devices is performed by the interface 740 having a communication function and operating under the control of the CPU 710. Interaction between the sales processing system 623 and the user is performed by the interface 740 having input and output devices, presenting information to the user via the output device and accepting user operations via the input device under the control of the CPU 710.

[0160] One or more of the above-mentioned programs may be recorded on the non-volatile recording medium 750. In this case, the interface 740 may read the program from the non-volatile recording medium 750. The CPU 710 may then either directly execute the program read by the interface 740, or temporarily save it in the main memory 720 or auxiliary memory 730 before executing it.

[0161] Alternatively, the processing of each component may be performed by recording a program for executing all or part of the processing performed by the price determination device 100, the sales processing system 200, the price determination device 610, the price determination device 621, and the sales processing system 623 on a computer-readable recording medium, and then loading and executing the program recorded on this recording medium into a computer system. The term "computer system" here includes hardware such as an operating system (OS) and peripheral devices. Further, the "computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, ROM (Read Only Memory), CD-ROM (Compact Disc Read Only Memory), and storage devices such as hard disks built into computer systems. The above program may be for realizing part of the functions described above, and may also be for realizing the functions described above in combination with a program already recorded in the computer system.

[0162] As described above, the embodiments of the present invention have been described in detail with reference to the drawings, but the specific configuration is not limited to these embodiments, and designs and the like within a scope that does not deviate from the gist of the present invention are also included. Further, the above-described embodiments may be appropriately combined with other embodiments.

[0163] Part or all of the above embodiments may also be described as in the following supplementary notes, but are not limited thereto.

[0164] (Supplementary Note 1) Price determining means that determines an offered price for a product with a limited sales period using a first price determining method before a predetermined method change time, and determines the price using a second price determining method after the method change time A price determining device comprising:

[0165] (Supplementary Note 2) In the first price determining method, the price determining means adjusts the expected demand for the next time step using a value obtained by multiplying the error between the actual remaining inventory quantity and a reference remaining inventory quantity that is a pre-planned remaining inventory quantity by a predetermined coefficient, and determines the offered price according to the adjusted demand, The price determining device according to Supplementary Note 1.

[0166] (Supplementary Note 3) The pre-planned remaining inventory quantity is calculated based on a reference demand that is a predicted demand value obtained by solving an optimization problem using an evaluation function indicating a cumulative value of profits expected in the sales period before the start of the sales period, In said first pricing method, said pricing means calculates said adjusted demand by adding a value obtained by multiplying said error by said coefficient to said reference demand, The pricing apparatus according to Supplementary Note 2.

[0167] (Supplementary Note 4) Said reference demand is calculated based on time steps and prices indicated by real numbers, so as to maximize the cumulative value of said profit, The pricing apparatus according to Supplementary Note 3.

[0168] (Supplementary Note 5) Said coefficient is calculated by solving an equation that maximizes the cumulative value of profit in said sales period, The pricing apparatus according to any one of Supplementary Notes 2 to 4.

[0169] (Supplementary Note 6) In said second pricing method, said pricing means calculates an offering price by inputting the actual remaining inventory quantity and time step into a pricing policy, wherein the pricing policy is a function that outputs an offering price in response to inputs of inventory quantity and time step, and is obtained by solving, before the start of said sales period, an optimization problem using an evaluation function that indicates the cumulative expected profit during the period in which said second pricing method is used, The pricing apparatus according to any one of Supplementary Notes 1 to 5.

[0170] (Supplementary Note 7) Said pricing policy is predetermined using demand distribution information that indicates, for each time step, the probability distribution of demand corresponding to the offering price, The pricing apparatus according to Supplementary Note 6.

[0171] (Supplementary Note 8) Comprising a pricing apparatus and a sales processing system, Said pricing apparatus comprises: pricing means that determines an offering price for a product with a finite sales period using a first pricing method before a predetermined method change time, and determines the offering price using a second pricing method after said method change time ​Sales management system.

[0172] (Note 9) The price determination means, in the first price determination method, adjusts the expected demand for the next time step using a value obtained by multiplying the error between the actual remaining inventory and the reference inventory (which is a predetermined remaining inventory) by a predetermined coefficient, and determines the quoted price according to the adjusted demand. The sales management system described in Appendix 8.

[0173] (Note 10) The aforementioned pre-planned remaining inventory quantity is calculated based on the reference demand, which is a forecast value of demand obtained by solving an optimization problem using an evaluation function that shows the cumulative value of expected profits during the sales period, before the start of the sales period. The price determination means, in the first price determination method, calculates the adjusted demand by adding the value obtained by multiplying the error by the coefficient to the reference demand. The sales management system described in Appendix 9.

[0174] (Note 11) The aforementioned reference demand is calculated based on the time step and the price expressed as a real value, in order to maximize the cumulative value of the aforementioned profit. The sales management system described in Appendix 10.

[0175] (Note 12) The coefficient is calculated by solving the equation that maximizes the cumulative value of profit during the sales period. A sales management system described in any one of the appendices 9 through 11.

[0176] (Note 13) The price determination means calculates the quoted price by inputting the actual remaining inventory and the time step into a price determination policy, which is a function obtained by solving an optimization problem before the start of the sales period, using a function that outputs a quoted price upon input of the inventory quantity and time step, and an evaluation function that shows the cumulative value of expected profit during the period in which the second price determination method is used. The sales management system according to any one of Supplementary Notes 8 to 12.

[0177] (Supplementary Note 14) The price determination policy is determined in advance using demand distribution information that indicates a probability distribution of demand according to an offered price for each time step, The sales management system according to Supplementary Note 13.

[0178] (Supplementary Note 15) by a computer, determining an offered price of a product with a finite sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the method change time, A price determination method comprising:

[0179] (Supplementary Note 16) In the first price determination method, the computer adjusts the demand assumed for the next time step by using a value obtained by multiplying an error between an actual remaining inventory quantity and a reference inventory quantity which is a pre-planned remaining inventory quantity by a predetermined coefficient, and determines the offered price according to the adjusted demand, The price determination method according to Supplementary Note 15.

[0180] (Supplementary Note 17) The pre-planned remaining inventory quantity is calculated based on a reference demand which is a predicted demand value obtained by solving an optimization problem using an evaluation function indicating a cumulative value of profit expected in the sales period before the start of the sales period, In the first price determination method, the computer calculates the adjusted demand by adding a value obtained by multiplying the error by the coefficient to the reference demand, The price determination method according to Supplementary Note 16.

[0181] (Supplementary Note 18) The reference demand is calculated based on a time step and a price represented as a real number so as to maximize the cumulative value of the profit, The price determination method according to Supplementary Note 17.

[0182] (Note 19) The coefficient is calculated by solving the equation that maximizes the cumulative value of profit during the sales period. The price determination method described in any one of the appendices 16 to 18.

[0183] (Note 20) The computer calculates the quoted price by inputting the actual remaining inventory and the time step into a price determination policy, which is a function obtained by solving an optimization problem before the start of the sales period, using a function that outputs a quoted price upon input of inventory quantity and time step, and an evaluation function that shows the cumulative value of expected profit during the period in which the second price determination method is used. The price determination method described in any one of the appendices 15 to 19.

[0184] (Note 21) The aforementioned price determination strategy is predetermined using demand distribution information that shows the probability distribution of demand corresponding to the offered price at each time step. The pricing method described in Appendix 20.

[0185] (Note 22) On the computer, The asking price of a product with a limited sales period shall be determined using a first price determination method before a predetermined time for method change, and after the said time for method change, A program that executes the command.

[0186] (Note 23) The computer is instructed to perform the following actions in the first price determination method: adjust the expected demand for the next time step using a value obtained by multiplying the error between the actual remaining inventory and the reference inventory (which is a pre-planned remaining inventory) by a predetermined coefficient, and then determine the quoted price according to the adjusted demand. The program described in Appendix 22.

[0187] (Note 24) The aforementioned pre-planned remaining inventory quantity is calculated based on the reference demand, which is a forecast value of demand obtained by solving an optimization problem using an evaluation function that shows the cumulative value of expected profits during the sales period, before the start of the sales period. The computer is instructed to perform the following in the first price determination method: calculate the adjusted demand by adding the value obtained by multiplying the error by the coefficient to the reference demand. The program described in Appendix 23.

[0188] (Note 25) The aforementioned reference demand is calculated based on the time step and the price expressed as a real value, in order to maximize the cumulative value of the aforementioned profit. The program described in Appendix 24.

[0189] (Note 26) The coefficient is calculated by solving the equation that maximizes the cumulative value of profit during the sales period. The program described in any one of the appendices 23 to 25.

[0190] (Note 27) The computer is instructed to calculate the quoted price by inputting the actual remaining inventory and the time step into a price determination policy, which is a function obtained by solving an optimization problem before the start of the sales period, using a function that takes the inventory quantity and time step as inputs and outputs a quoted price, and an evaluation function that shows the cumulative value of expected profit during the period in which the second price determination method is used. The program described in any one of the appendices 22 to 26.

[0191] (Note 28) The aforementioned price determination strategy is predetermined using demand distribution information that shows the probability distribution of demand corresponding to the offered price at each time step. The program described in Appendix 27. [Explanation of Symbols]

[0192] 1,620 Sales Management System 100, 610, 621 Price determination device 110 Communications Department 120 Display section 130 Operation Input Section 180 Storage section 190 Processing Unit 191 Pre-calculation section 192, 611, 622 Price determination section 200,623 Sales Processing System

Claims

1. A price determination means for determining the asking price of a product with a limited sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the said method change time. A price determination device equipped with the following features.

2. The price determination means, in the first price determination method, adjusts the expected demand for the next time step using a value obtained by multiplying the error between the actual remaining inventory and the reference inventory (which is a predetermined remaining inventory) by a predetermined coefficient, and determines the quoted price according to the adjusted demand. The price determination device according to claim 1.

3. The aforementioned pre-planned remaining inventory quantity is calculated based on the reference demand, which is a forecast value of demand obtained by solving an optimization problem using an evaluation function that shows the cumulative value of expected profits during the sales period, before the start of the sales period. The price determination means, in the first price determination method, calculates the adjusted demand by adding the value obtained by multiplying the error by the coefficient to the reference demand. The price determination device according to claim 2.

4. The aforementioned reference demand is calculated based on the time step and the price expressed as a real value, in order to maximize the cumulative value of the aforementioned profit. The price determination device according to claim 3.

5. The coefficient is calculated by solving the equation that maximizes the cumulative value of profit during the sales period. The price determination device according to claim 2.

6. The price determination means calculates the quoted price by inputting the actual remaining inventory and the time step into a price determination policy, which is a function obtained by solving an optimization problem before the start of the sales period, using a function that outputs a quoted price upon input of inventory quantity and time step, and an evaluation function that shows the cumulative value of expected profit during the period in which the second price determination method is used. The price determination device according to claim 1.

7. The aforementioned price determination strategy is predetermined using demand distribution information that shows the probability distribution of demand corresponding to the offered price at each time step. The price determination device according to claim 6.

8. It includes a price determination device and a sales processing system, The price determination device is A price determination means for determining the asking price of a product with a limited sales period using a first price determination method before a predetermined method change time, and using a second price determination method after the said method change time. Equipped with Sales management system.

9. Computers The asking price of a product with a limited sales period is determined using a first price determination method before a predetermined time for a method change, and after that time for a method change, it is determined using a second price determination method. A pricing method that includes the following.

10. On the computer, The asking price of a product with a limited sales period shall be determined using a first price determination method before a predetermined time for method change, and after the said time for method change, A program that executes the command.

Images