CN110826823A - Pricing strategy evaluation method and system - Google Patents

Pricing strategy evaluation method and system Download PDF

Info

Publication number
CN110826823A
CN110826823A CN201810891316.2A CN201810891316A CN110826823A CN 110826823 A CN110826823 A CN 110826823A CN 201810891316 A CN201810891316 A CN 201810891316A CN 110826823 A CN110826823 A CN 110826823A
Authority
CN
China
Prior art keywords
model
commodity
user
price
simulation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810891316.2A
Other languages
Chinese (zh)
Inventor
吴雨淋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201810891316.2A priority Critical patent/CN110826823A/en
Publication of CN110826823A publication Critical patent/CN110826823A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0283—Price estimation or determination

Abstract

The invention discloses a pricing strategy evaluation method and system, and relates to the technical field of computers. One embodiment of the method comprises: generating a user model and a commodity model according to the real service data, and establishing a simulation system by using the user model and the commodity model; in the simulation system, a user model determines whether to purchase a commodity model according to the selection probability of the user model on the commodity model; the selection probability is related to the current price of the commodity model; executing a first simulation process and a second simulation process in the simulation system; the current price of the commodity model in the first simulation process is determined according to the initial price of the commodity model, and the current price of the commodity model in the second simulation process is determined according to the initial price of the commodity model and a pricing strategy to be evaluated; the trade totals of the first simulation process and the second simulation process are compared to evaluate the pricing strategy. The embodiment can effectively evaluate the pricing strategy on the premise of not influencing actual business.

Description

Pricing strategy evaluation method and system
Technical Field
The invention relates to the technical field of computers, in particular to a pricing strategy evaluation method and system.
Background
In real life, a service party often needs to continuously adjust the price of a commodity according to market demand to maximize profit level, and a basic pricing strategy is to predict the commodity demand based on a price elasticity principle. The flexibility refers to the sensitivity of the change of the commodity demand with the price change. Due to the non-linear relationship between commodity price and sales and the existence of a large amount of noise data, the effect of the pricing strategy presents uncertainty and needs to be evaluated.
Currently, the common evaluation method is an a/B experiment method, which divides the commodity into two groups, one group is an experiment group for executing a pricing strategy, and the other group is a control group for keeping the original pricing; the pricing strategy can be evaluated by comparing the revenue of the two groups after a period of sale.
In the process of implementing the invention, the inventor finds that the prior art has at least the following problems:
1. since the commodity attributes are different and there may be a relationship of pulling or competing with each other, it is difficult to fairly divide the experimental group and the control group.
2. The pricing strategy to be evaluated may cause loss to the actual traffic as it is not yet verified.
3. In the process of the A/B experiment method, the experiment process needs to be controlled to avoid the influence of events such as promotion and the like, which interferes with the normal operation mechanism.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and a system for evaluating a pricing policy, which can establish a simulation system simulating a real market according to real service data, and perform the pricing policy in the simulation system, that is, can accurately evaluate the pricing policy without affecting actual services.
To achieve the above object, according to one aspect of the present invention, there is provided an evaluation method of a pricing strategy.
The pricing strategy evaluation method provided by the embodiment of the invention comprises the following steps: generating a user model corresponding to a real user and a commodity model corresponding to a real commodity according to the real service data, and establishing a simulation system by using the user model and the commodity model; in the simulation system, a user model determines whether to purchase a commodity model according to the selection probability of the user model on the commodity model; the selection probability is related to the current price of the commodity model; executing a first simulation process and a second simulation process in the simulation system, and respectively storing transaction data of the first simulation process and the second simulation process; the current price of any commodity model in the first simulation process is determined according to the initial price of the commodity model, and the current price of any commodity model in the second simulation process is determined according to the initial price of the commodity model and a pricing strategy to be evaluated; the trading totals of the first simulation process and the second simulation process are compared to evaluate the pricing strategy.
Optionally, the real commodities are commodities in the same category; any user model is provided with at least one of the following parameters: a spending willingness index, a brand preference index, a performance demand index; any commodity model is provided with at least one of the following parameters: performance index, brand value index, price sensitivity, brand sensitivity, performance sensitivity; the expenditure willingness index is determined according to the price of the real commodity purchased and/or browsed by the real user corresponding to the user model; the brand preference index is determined according to the browsing times of the real users corresponding to the user model aiming at the real commodities of different brands; the performance demand index is determined according to the performance index of the real commodity purchased and/or browsed by the real user corresponding to the user model; the brand value index is determined according to the evaluation scores of real commodities with the commodity model brand; different commodity models are provided with the same price sensitivity, brand sensitivity and performance sensitivity.
Optionally, the creating a simulation system using a user model and a commodity model includes: setting a simulation period, the number of user models in the current simulation period, a simulation step length, a price floating strategy and a replenishment strategy; uniformly sampling three dimensions of a spending will index, a brand preference index and a performance demand index aiming at a user model generated according to real service data to obtain a user model of the current simulation period; determining the number of user models of the current simulation step length according to the Poisson distribution; and randomly sampling in the user model of the current simulation period according to the number to obtain the user model of the current simulation step length.
Optionally, the selection probability is determined by the total utility value of the commodity model to the user model; the total utility value is the sum of the price utility value, the brand utility value, the performance utility value and the inherent utility value of the commodity model to the user model; wherein the price utility value is: the product of the price sensitivity and the quotient of the expenditure willingness index of the user model and the current price of the commodity model; the brand utility value is: the product of a brand preference index of a user model for a commodity model, a brand value index of the commodity model and the brand sensitivity; the performance utility values are: a product of a performance demand index of the user model, a performance index of the commodity model, and the performance sensitivity.
Optionally, the method further comprises: in the simulation system: if the sum of the selection probabilities of the user model to each commodity model is larger than a preset threshold value, randomly purchasing a commodity model according to the selection probabilities; and entering a waiting state if the sum of the selection probabilities of the user model to each commodity model is not greater than the threshold value.
Optionally, the determining, by the current price of any commodity model in the first simulation process according to the initial price thereof, specifically includes: when the first simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the price floating strategy; the current price of any commodity model in the second simulation process is determined according to the initial price and the pricing strategy to be evaluated, and the method specifically comprises the following steps: when the second simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the pricing strategy and the price floating strategy; wherein the pricing strategy adjusts the current price of the commodity model based on the transaction data in the second simulation process.
Optionally, the simulation time of the first simulation process is the same as that of the second simulation process, and the transaction total includes: total sales, and/or total profit.
To achieve the above object, according to another aspect of the present invention, there is provided an evaluation system of a pricing strategy.
The pricing strategy evaluation system of the embodiment of the invention can comprise: the modeling unit is used for generating a user model corresponding to a real user and a commodity model corresponding to a real commodity according to real service data, and establishing a simulation system by utilizing the user model and the commodity model; in the simulation system, a user model determines whether to purchase a commodity model according to the selection probability of the user model on the commodity model; the selection probability is related to the current price of the commodity model; the execution unit is used for executing a first simulation process and a second simulation process in the simulation system and respectively storing the transaction data of the first simulation process and the second simulation process; the current price of any commodity model in the first simulation process is determined according to the initial price of the commodity model, and the current price of any commodity model in the second simulation process is determined according to the initial price of the commodity model and a pricing strategy to be evaluated; and the evaluation unit is used for comparing the transaction total of the first simulation process and the second simulation process so as to evaluate the pricing strategy.
Optionally, the real commodities are commodities in the same category; any user model is provided with at least one of the following parameters: a spending willingness index, a brand preference index, a performance demand index; any commodity model is provided with at least one of the following parameters: performance index, brand value index, price sensitivity, brand sensitivity, performance sensitivity; the expenditure willingness index is determined according to the price of the real commodity purchased and/or browsed by the real user corresponding to the user model; the brand preference index is determined according to the browsing times of the real users corresponding to the user model aiming at the real commodities of different brands; the performance demand index is determined according to the performance index of the real commodity purchased and/or browsed by the real user corresponding to the user model; the brand value index is determined according to the evaluation scores of real commodities with the commodity model brand; different commodity models are provided with the same price sensitivity, brand sensitivity and performance sensitivity.
Optionally, the modeling unit may be further configured to: setting a simulation period, the number of user models in the current simulation period, a simulation step length, a price floating strategy and a replenishment strategy; uniformly sampling three dimensions of a spending will index, a brand preference index and a performance demand index aiming at a user model generated according to real service data to obtain a user model of the current simulation period; determining the number of user models of the current simulation step length according to the Poisson distribution; and randomly sampling in the user model of the current simulation period according to the number to obtain the user model of the current simulation step length.
Optionally, the selection probability is determined by the total utility value of the commodity model to the user model; the total utility value is the sum of the price utility value, the brand utility value, the performance utility value and the inherent utility value of the commodity model to the user model; wherein the price utility value is: the product of the price sensitivity and the quotient of the expenditure willingness index of the user model and the current price of the commodity model; the brand utility value is: the product of a brand preference index of a user model for a commodity model, a brand value index of the commodity model and the brand sensitivity; the performance utility values are: a product of a performance demand index of the user model, a performance index of the commodity model, and the performance sensitivity.
Optionally, the modeling unit may be further configured to implement: in the simulation system: if the sum of the selection probabilities of the user model to each commodity model is larger than a preset threshold value, randomly purchasing a commodity model according to the selection probabilities; and entering a waiting state if the sum of the selection probabilities of the user model to each commodity model is not greater than the threshold value.
Optionally, the execution unit may be further configured to implement: when the first simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the price floating strategy; when the second simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the pricing strategy and the price floating strategy; wherein the pricing strategy adjusts the current price of the commodity model based on the transaction data in the second simulation process.
Optionally, the simulation time of the first simulation process is the same as that of the second simulation process, and the transaction total includes: total sales, and/or total profit.
To achieve the above object, according to still another aspect of the present invention, there is provided an electronic apparatus.
An electronic device of the present invention includes: one or more processors; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the method for evaluating a pricing policy provided by the present invention.
To achieve the above object, according to still another aspect of the present invention, there is provided a computer-readable storage medium.
A computer-readable storage medium of the present invention has stored thereon a computer program that, when executed by a processor, implements the method of evaluating a pricing strategy provided by the present invention.
According to the technical scheme of the invention, one embodiment of the invention has the following advantages or beneficial effects:
firstly, a user model corresponding to a real user and a commodity model corresponding to a real commodity are generated according to real commodity information, transaction information, browsing information, evaluation information and the like, and a simulation system is established based on the user model and the commodity model and used for respectively executing an original strategy and a pricing strategy so as to evaluate the pricing strategy. Therefore, the pricing strategy can be accurately evaluated on the premise of not influencing actual services, and the problems of difficult implementation, high risk, high cost and the like in the prior art are solved.
Secondly, in order to accurately simulate the real market, various parameters such as a expenditure willingness index, a brand preference index, a performance index of a commodity model, a brand value index and the like of the user model are extracted, a complete total utility value calculation formula is established, the selection probability of the commodity model by the user model is further determined (finally, a purchase mechanism in the simulation system is realized), and complex user behaviors and interaction mechanisms are realized in the simulation system, so that the reliability of the pricing strategy evaluation method is improved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of a pricing strategy evaluation method according to an embodiment of the invention;
FIG. 2 is a diagram illustrating an implementation of a pricing policy evaluation method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of components of an evaluation system for pricing strategies in accordance with an embodiment of the invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 5 is a schematic structural diagram of an electronic device for implementing the pricing policy evaluation method according to the embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Because the existing pricing strategy evaluation methods such as the A/B experiment method and the like are directly executed in the actual business process, the method has the defects of difficult implementation, high risk, high cost and the like. In order to solve the problem, the invention establishes a simulation system of a real market according to real service information, a first simulation process adopting an original strategy (namely an original price strategy) and a second simulation process adopting a pricing strategy to be evaluated are respectively executed, and finally, the total transaction amount (such as sales total amount and profit total amount) of the two simulation processes is compared to evaluate the pricing strategy. Where a simulation process refers to a time phase in which an independent instance is executed in a simulation system, a simulation process may correspond to one or more simulation cycles. The first simulation process and the second simulation process are independent simulation processes, and the first simulation process and the second simulation process can be executed according to a certain sequence or simultaneously. Therefore, the pricing strategy can be evaluated on the premise of not influencing actual services. The technical solution of the present invention will be described in detail below.
It is to be understood that the terms "first," "second," and the like as used herein are used herein to describe various concepts, but these concepts are not limited by the terms described above. The above terms are only used to distinguish one concept from another. For example, the first simulation process may be referred to as a second simulation process, or the second simulation process may be referred to as a first simulation process, and the first simulation process and the second simulation process are both simulation processes, but are not the same simulation process, without departing from the scope of the present invention.
It should be noted that the embodiments of the present invention and the technical features of the embodiments may be combined with each other without conflict.
Fig. 1 is a schematic diagram of the main steps of a pricing strategy evaluation method according to an embodiment of the present invention.
As shown in fig. 1, the method according to the embodiment of the present invention may be specifically performed according to the following steps:
step S101: and generating a user model corresponding to the real user and a commodity model corresponding to the real commodity according to the real service data, and establishing a simulation system by using the user model and the commodity model.
In this step, the real service data may be data derived from each real service database, such as commodity data of commodity identification, commodity category, brand, cost price, open quotation, daily average stock, etc., transaction data of transaction user identification, purchased commodity identification, transaction price, transaction quantity, transaction time, etc., browsing data of browsing user identification, browsing commodity identification, browsing duration, etc., and evaluation data of evaluation user identification, evaluation commodity identification, commodity scoring, etc.
In practical application, all or part of users in a certain time period can be selected to generate a user model in the simulation system, and part of commodities can be selected to generate a commodity model in the simulation system according to a certain strategy. It can be understood that the selected users and commodities are real users and real commodities. Preferably, in order to accurately evaluate the pricing strategy implementation effect, commodities with competition relations in the same category can be selected to generate a commodity model. The categories may be commodity categories of various granularities, among others. In a specific application, if the effect of the pricing strategy in a market formed by multiple types of commodities needs to be evaluated, the market can be converted into subsets which only contain the same type of commodities to be evaluated respectively.
In the embodiment of the invention, the user models corresponding to the selected users one by one can be established according to the selected users, and the parameters of the user models can be a expenditure willingness index, a brand preference index and a performance demand index. The expenditure willingness index is used for representing the price bearing capacity of the user, the brand preference index is used for representing the preference degree of the user for each commodity brand, and the performance demand index is used for representing the demand of the user for the performance of the commodity.
Preferably, the willingness-to-expenditure index may be a weighted average of the prices at which the user purchased and browsed the category of items. In an actual scene, if the user purchases the category of commodities and browses other commodities of the category at the same time, a higher weight value can be set for the purchased commodities, a lower weight value can be set for the browsed commodities, and a weighted average value of commodity prices is calculated to serve as a spending willingness index. If the user does not purchase the category of commodities and only browses the plurality of commodities in the category, a weight value can be set for the browsed commodities according to the browsing time length (the weight value is positively correlated with the browsing time length), and a weighted average value of commodity prices is calculated to serve as a spending willingness index.
The brand preference index of a user for a certain brand may be the quotient of the number of times the user browses the brand of goods and the number of times the user browses all the goods. It can be understood that the browsing times can reflect the preference degree of the user to the brand of the commodity, and the normalization processing according to the browsing times of the user to the commodities of all brands can enable the brand preference indexes of different users to be compared with each other. It can be understood that in a specific application scene, different weight values can be set according to browsing duration of each browsing to calculate a brand preference index, so that the brand preference degree of a user can be more accurately measured.
The performance demand index may be determined based on a performance index (performance index will be described below) of the user's purchase and browsing of goods. Specifically, if the user purchases the category of goods and browses other goods of the category at the same time, a higher weight value may be set for the purchased goods, a lower weight value may be set for the browsed goods, and a weighted average of the performance indexes of the goods may be calculated as the performance demand index. If the user does not purchase the category of commodities and only browses the plurality of commodities in the category, a weight value (the weight value is in positive correlation with the browsing time length) can be set for the browsed commodities according to the browsing time length, and the weighted average value of the commodity performance indexes is calculated to serve as the performance demand index.
It is to be understood that in a specific application, one or more of the above parameters may be set for the user model according to a service requirement, and one or more other parameters may also be added to the user model based on the real service data, which is not limited in the present invention.
As a preferred scheme, the parameters of the commodity model may be: performance index, brand value index, price sensitivity, brand sensitivity, performance sensitivity. The performance index is used for quantifying and integrating various software and hardware configuration parameters and functional parameters of the commodity, so that the overall performance of the commodity is visually reflected; the brand value index is used for representing the influence of the commodity brand on the user group; the price sensitivity, the brand sensitivity and the performance sensitivity are the integral sensitivity of a user group (namely, a selected real user) to all commodities (namely, selected commodities in the same category); wherein, the price sensitivity can measure the degree of the commodity price driven by the user to purchase the commodity motivation, the brand sensitivity can measure the degree of the commodity brand driven by the user to purchase the commodity motivation, and the performance sensitivity can measure the degree of the commodity performance driven by the user to purchase the commodity motivation.
In an optional implementation manner, the performance index may be obtained by integrating different configuration parameters and functional parameters of the commodity and performing weighted summation. For example, for the category of the mobile phone, different weight values may be set for the processor, the running memory, the resolution of the camera, and other dimensions, and the scores of the product in the dimensions are weighted and summed according to the set weight values, so as to obtain the performance index of the product.
The brand value index may be a weighted average of the valuation scores of all the goods under the brand of the good. When calculating, the weight value of a certain product may be the quotient of the sales volume of the product in a time period and the total sales volume of all products under the brand of the product in the time period.
Price sensitivity, brand sensitivity, performance sensitivity take the same value for different commodities, which reflects the overall sensitivity level of the user population for all commodities. The three can be calculated by a total utility value formula. Specifically, the total utility value formula is as follows:
Uij＝β1(xi1/yj1)+β2xi2yj2+β3xi3yj3+Cj
wherein i is a user identifier, j is a commodity identifier, and UijFor the total utility value of the commodity j to the user i (used to characterize the overall value of the commodity to the user), xi1Is the willingness-to-pay index, x, of the user ii2Brand preference index, x, for user i to brand ji3Is a performance requirement index, y, of user ij1Is the current price of item j, yj2Is the brand value index, y, of the good jj3Is the Performance index of commercial product j, β1、β2、β3Price sensitivity, brand sensitivity, performance sensitivity, CjIs the intrinsic utility value of commodity j (used to measure the value of commodity j beyond price, brand, performance.) it is understood that β in the above formula1(xi1/yj1) For the price utility value of item j to user i, β2xi2yj2Brand utility value for item j to user i, β3xi3yj3And the total utility value is the sum of the price utility value, the brand utility value, the performance utility value and the inherent utility value of the commodity model.
It can be understood that the total utility value of the commodity to the user is related to the purchase possibility of the user, the purchase possibility is negatively related to the commodity price, and is positively related to commodity performance, brand value, user expenditure willingness, performance requirements and brand preference, so that the interaction behavior of the user and the commodity in the real market can be accurately simulated through the total utility value formula.
In fact, the probability of selection of a user when facing an item may be determined by the total utility value of the item to the user. Specifically, the selection probability P of the user i to the commodity jijCan be calculated according to the following formula:
wherein k is the identification of any commodity in the commodity set faced by the user i, and U isikIs the total utility value of the commodity k to the user i.
In practice, the selection probability calculation β may be used as described above1、β2、β3Specifically, the expenditure willingness indexes, the brand preference indexes, the performance demand indexes of different users, the performance indexes of actual purchased commodities and the brand value indexes can be input into the total utility value formula, the selection probability of the user on the purchased commodities is further written, then the product of the selection probabilities is used as a likelihood function, and finally the log likelihood equation corresponding to the likelihood function is solved to determine β1、β2、β3And an intrinsic utility value C for each purchased itemj。
Through the parameter setting, the user model and the commodity model can be made to conform to a real scene to the maximum extent, and the subsequent establishment of a simulation system similar to a real market is facilitated. It can be understood that, because the user model corresponds to the real user one to one, and the commodity model corresponds to the real commodity one to one, various parameters of the user model are parameters of the corresponding real user, various parameters of the commodity model are parameters of the corresponding real commodity, a total utility value of the commodity model to the user model is a total utility value of the corresponding commodity to the user, a selection probability of the user model to the commodity model is a selection probability of the corresponding user to the commodity, a price of the commodity model is a price of the corresponding commodity, and a brand of the commodity model is a brand of the corresponding commodity.
In an embodiment of the invention, the simulation system may be built according to the following steps:
1. and setting a simulation period and a simulation step length. The simulation cycle is used as macroscopic time measurement of the simulation system, the simulation step is microscopic time measurement in the simulation cycle, and the quotient of the simulation cycle and the simulation step is simulation times. In a specific application, the simulation period can be set to one year, and the simulation step length can be set to one day.
2. And setting the number of user models in the current simulation period according to the total number of the user models, and uniformly sampling from three dimensions of a spending will index, a brand preference index and a performance demand index in all the user models to obtain the user models in the current simulation period of the number.
3. And determining the number of user models of the current simulation step length according to the Poisson distribution based on the number of the user models of the current simulation period. It is understood that the use of a poisson distribution can simulate the user arrival probability distribution of a real market. And then randomly sampling in the user model of the current simulation period to obtain the user models of the current simulation step length of the number.
4. And setting a price floating strategy and a replenishment strategy of the current simulation period to simulate a real market. The price floating strategy comprises commodities needing price adjustment, adjustment strength and adjustment time. It should be noted that the price floating strategy is set according to events such as sales promotion in a simulated real scene, and is not related to the pricing strategy to be evaluated, and the two strategies can independently realize the adjustment of the current price of the commodity model.
5. A purchase mechanism is established. Specifically, in the simulation system, the user model determines whether to purchase the commodity model according to the selection probability of the user model on the commodity model. As can be seen from the foregoing description, the selection probability is determined by the total utility value of the commodity model to the user model, and for a certain user model and a certain commodity model, the willingness-to-expenditure index, the brand preference index, the performance demand index, the performance index, the brand value index, the price sensitivity, the brand sensitivity, and the performance sensitivity in the total utility value formula are fixed values, so the total utility value is determined by the current price of the commodity model.
In the simulation system, the user models in the current simulation period and the current simulation step length can traverse the commodity models, and the selection probability of each commodity model is calculated to determine whether to purchase. As a preferred scheme, if the sum of the selection probabilities is greater than a preset threshold, the user model randomly selects a commodity model according to the selection probability of the user model to each commodity for purchase; if the sum of the selection probabilities is not greater than the threshold, the user model enters a wait state. In addition, the user model entering the waiting state can recalculate each selection probability and judge whether to purchase or not after the current price of the commodity model is adjusted until the simulation step length is finished.
Preferably, in the simulation system, one user model can only purchase at most one commodity model, the user model which has purchased the commodity model can be removed from the simulation system, and the user model which is in a waiting state can be put into a subsequent simulation step length for continuous judgment.
Through the steps, a simulation system for accurately simulating a real market can be established based on the user model and the commodity model, and a complex user behavior and interaction mechanism is realized in the simulation system, so that the accuracy and reliability of subsequent pricing strategy evaluation are improved.
Step S102: executing a first simulation process and a second simulation process in the simulation system, and respectively storing transaction data of the first simulation process and the second simulation process.
In this step, the first simulation process and the second simulation process are completely independent simulation instances. In practical application, the simulation time of the two can be set to be the same, so that subsequent benefit analysis is facilitated.
In particular, in the embodiment of the present invention, the current price of any commodity model in the first simulation process is determined according to the initial price thereof, that is, the current price of the commodity model in the first simulation process is kept at the initial price thereof without being influenced by other factors. The initial price refers to the price of the real commodity corresponding to the commodity model when the simulation system is established. The current price of any commodity model in the second simulation process is determined according to the initial price and the pricing strategy to be evaluated, namely under the condition that no other factors influence exists, the current price of the commodity model in the first simulation process is the adjusted price based on the pricing strategy on the basis of the initial price.
Generally, pricing policies are often adjusted based on transactional data (i.e., data related to the purchase of models of goods by models of users) in the second simulation process. When the data volume of the transaction data is less, the pricing strategy can also adjust the current price of the commodity model by means of the real transaction data of the business database. In addition, pricing strategies often perform price adjustment on part of the commodity models in a period of several days, and the price of the adjusted commodity models is kept unchanged for a long time.
If a price floating strategy is set in the simulation system, for the first simulation process: when starting, the current price of any commodity model is equal to the initial price; after starting, the current price of any commodity model is adjusted according to a price floating strategy; for the second simulation procedure: when starting, the current price of any commodity model is equal to the initial price; after startup, the current price of any commodity model is adjusted according to the pricing strategy and the price floating strategy. Since the price floating policy affects both simulation processes simultaneously, it does not affect the final evaluation of the pricing policy.
Step S103: the trade totals of the first simulation process and the second simulation process are compared to evaluate the pricing strategy.
In this step, the transaction data can be counted after the simulation process is finished to obtain transaction total data such as sales total, profit total and the like, and the pricing strategy can be evaluated by analyzing the transaction total data. In practical application, one or two of the total sales and the total profit can be compared to obtain the evaluation result. For example, if the total sales amount of the second simulation process is increased by more than a preset percentage than the first simulation process and the total profit amount of the second simulation process is increased by more than another preset percentage than the first simulation process, it may be determined that the pricing strategy is implemented well.
Fig. 2 is a schematic diagram of a specific implementation of the pricing policy evaluation method according to an embodiment of the present invention.
As shown in fig. 2, the pricing policy evaluation method in the embodiment of the present invention may be implemented by interaction of a service database, a simulation system, a simulation database, and a pricing device.
Specifically, the business database provides various business data of real users and real commodities, and is composed of a commodity information base, a transaction information base, a flow information base and an evaluation information base. The commodity information base is used for storing commodity basic data such as commodity identification, commodity category, brand, cost price, public quotation, daily average stock and the like; the transaction information base is used for storing various transaction data of the commodities purchased by the user, such as transaction user identification, commodity purchasing identification, transaction price, transaction quantity, transaction time and the like; the flow information base is used for storing browsing data such as browsing user identification, browsing commodity identification, browsing duration and the like; the evaluation information base is used for storing evaluation data such as evaluation user identification, evaluation commodity identification and commodity scoring.
The simulation system consists of a modeling component, a scene definition component, a simulation operation component and a profit analysis component. The modeling component is used for acquiring real business data from a business database and generating a user model and a commodity model; the scene definition component is used for setting simulation periods, simulation step sizes, the number of user models in each simulation period, the probability distribution of the number of users arriving in each simulation step size, a price floating strategy and a replenishment strategy; the simulation operation component is used for determining a specific user model and commodity model of each simulation period and each simulation step length, establishing a purchase mechanism based on selection probability, and placing the selected user model and commodity model into a simulation system to generate simulation transaction data; and the profit analysis component is used for obtaining transaction total through analyzing the simulated transaction data so as to evaluate the pricing strategy.
Wherein, the simulation operation component can execute the following steps in the second simulation process:
1. when the simulation is started, reading data such as a simulation period, a simulation step length, the number of user models in the current simulation period, a price floating strategy, a replenishment strategy, a pricing strategy execution period and the like in the scene definition component.
2. And reading the commodity model and the current price data thereof from the simulation database.
3. And reading all the user models from the simulation database, and uniformly sampling according to the number of the user models in the current simulation period to generate the user models in the current simulation period. This step can ensure that the user distribution of the simulation period is similar to the user distribution in the real market.
4. A simulation step size is started.
5. If the current moment exceeds the simulation period, the simulation execution is determined to be finished; if not, the transaction activity of the current simulation step size is simulated.
6. Determining the number of user models of the current simulation step length according to the Poisson distribution; and randomly sampling in the user model of the current simulation period according to the number to obtain the user model of the current simulation step length.
7. And traversing each user model, and determining the transaction behavior of each user model by calculating the selection probability of each user model to each commodity model.
8. And recording all transaction data of the current simulation step length into a simulation database.
9. And executing a price floating strategy and a replenishment strategy according to the corresponding trigger time.
10. And executing a pricing strategy according to the triggering time, and adjusting the current price of the commodity model based on the transaction data in the service database and the simulation database.
The simulation database is used for storing various data required by or generated by the simulation system and consists of a commodity information base, a transaction information base, a commodity model base and a user model base. The commodity information base is used for storing data such as identification of the commodity model, current price and the like; the transaction information base is used for storing simulation transaction data; the commodity model library is used for storing all commodity models; the user model library is used for storing all user models.
The pricing device is used for executing a pricing strategy to be evaluated, and can calculate the current price of the commodity model based on simulated transaction data (transaction data in a business database can be used when the initial simulated data volume is small), so that the dynamic adjustment of the commodity model price is realized. It will be appreciated that the first simulation process should not have access to the pricing means and the second simulation process requires access to the pricing means.
In the embodiment of the invention, a user model corresponding to a real user and a commodity model corresponding to a real commodity are generated according to real commodity information, transaction information, browsing information, evaluation information and the like, and a simulation system is established based on the user model and the commodity model and is used for respectively executing an original strategy and a pricing strategy so as to evaluate the pricing strategy. Therefore, the pricing strategy can be accurately evaluated on the premise of not influencing actual services, and the problems of difficult implementation, high risk, high cost and the like in the prior art are solved. In addition, in order to accurately simulate the real market, various parameters such as a expenditure willingness index, a brand preference index, a performance index of a commodity model, a brand value index and the like of the user model are extracted, a complete total utility value calculation formula is established so as to determine the selection probability of the commodity model by the user model, and a complex user behavior and interaction mechanism is realized in a simulation system, so that the reliability of the pricing strategy evaluation method is improved.
It should be noted that, for the convenience of description, the foregoing method embodiments are described as a series of acts, but those skilled in the art will appreciate that the present invention is not limited by the order of acts described, and that some steps may in fact be performed in other orders or concurrently. Moreover, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no acts or modules are necessarily required to implement the invention.
To facilitate a better implementation of the above-described aspects of embodiments of the present invention, the following also provides related systems for implementing the above-described aspects.
Referring to fig. 3, an evaluation system 300 for a pricing strategy according to an embodiment of the present invention may include a modeling unit 301, an execution unit 302, and an evaluation unit 303.
The modeling unit 301 may be configured to generate a user model corresponding to a real user and a commodity model corresponding to a real commodity according to real service data, and establish a simulation system using the user model and the commodity model; in the simulation system, a user model determines whether to purchase a commodity model according to the selection probability of the user model on the commodity model; the selection probability is related to the current price of the commodity model.
The execution unit 302 may be configured to execute a first simulation process and a second simulation process in the simulation system, and store transaction data of the first simulation process and the second simulation process, respectively; the current price of any commodity model in the first simulation process is determined according to the initial price of the commodity model, and the current price of any commodity model in the second simulation process is determined according to the initial price of the commodity model and a pricing strategy to be evaluated.
The evaluation unit 303 may be configured to compare the trade sums of the first simulation process and the second simulation process to evaluate the pricing strategy.
In the embodiment of the invention, the real commodities are commodities in the same category; any user model is provided with at least one of the following parameters: a spending willingness index, a brand preference index, a performance demand index; any commodity model is provided with at least one of the following parameters: performance index, brand value index, price sensitivity, brand sensitivity, performance sensitivity; the expenditure willingness index is determined according to the price of the real commodity purchased and/or browsed by the real user corresponding to the user model; the brand preference index is determined according to the browsing times of the real users corresponding to the user model aiming at the real commodities of different brands; the performance demand index is determined according to the performance index of the real commodity purchased and/or browsed by the real user corresponding to the user model; the brand value index is determined according to the evaluation scores of real commodities with the commodity model brand; different commodity models are provided with the same price sensitivity, brand sensitivity and performance sensitivity.
As a preferred solution, the modeling unit 301 may further be configured to: setting a simulation period, the number of user models in the current simulation period, a simulation step length, a price floating strategy and a replenishment strategy; uniformly sampling three dimensions of a spending will index, a brand preference index and a performance demand index aiming at a user model generated according to real service data to obtain a user model of the current simulation period; determining the number of user models of the current simulation step length according to the Poisson distribution; and randomly sampling in the user model of the current simulation period according to the number to obtain the user model of the current simulation step length.
Preferably, the selection probability is determined by the total utility value of the commodity model to the user model; the total utility value is the sum of the price utility value, the brand utility value, the performance utility value and the inherent utility value of the commodity model to the user model; wherein the price utility value is: the product of the price sensitivity and the quotient of the expenditure willingness index of the user model and the current price of the commodity model; the brand utility value is: the product of a brand preference index of a user model for a commodity model, a brand value index of the commodity model and the brand sensitivity; the performance utility values are: a product of a performance demand index of the user model, a performance index of the commodity model, and the performance sensitivity.
In practical applications, the modeling unit 301 may further be configured to: in the simulation system: if the sum of the selection probabilities of the user model to each commodity model is larger than a preset threshold value, randomly purchasing a commodity model according to the selection probabilities; and entering a waiting state if the sum of the selection probabilities of the user model to each commodity model is not greater than the threshold value.
In an alternative implementation, the execution unit 302 may be further configured to implement: when the first simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the price floating strategy; when the second simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the pricing strategy and the price floating strategy; wherein the pricing strategy adjusts the current price of the commodity model based on the transaction data in the second simulation process.
Furthermore, in an embodiment of the present invention, the simulation time of the first simulation process is the same as that of the second simulation process, and the transaction total includes: total sales, and/or total profit.
In the embodiment of the invention, a user model corresponding to a real user and a commodity model corresponding to a real commodity are generated according to real commodity information, transaction information, browsing information, evaluation information and the like, and a simulation system is established based on the user model and the commodity model and is used for respectively executing an original strategy and a pricing strategy so as to evaluate the pricing strategy. Therefore, the pricing strategy can be accurately evaluated on the premise of not influencing actual services, and the problems of difficult implementation, high risk, high cost and the like in the prior art are solved. In addition, in order to accurately simulate the real market, various parameters such as a expenditure willingness index, a brand preference index, a performance index of a commodity model, a brand value index and the like of the user model are extracted, a complete total utility value calculation formula is established so as to determine the selection probability of the commodity model by the user model, and a complex user behavior and interaction mechanism is realized in a simulation system, so that the reliability of the pricing strategy evaluation method is improved.
Fig. 4 shows an exemplary system architecture 400 of an evaluation method of a pricing policy or an evaluation system of a pricing policy to which an embodiment of the present invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405 (this architecture is merely an example, and the components included in a particular architecture may be adapted according to application specific circumstances). The network 404 serves as a medium for providing communication links between the terminal devices 401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. The terminal devices 401, 402, 403 may have installed thereon various communication client applications, such as a market emulation-type application, a web browser application, a search-type application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only).
The terminal devices 401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 405 may be a server providing various services, such as an emulation server (for example only) providing support for a market emulation-like application operated by a user with a terminal device 401, 402, 403. The background management server may process the received simulation instance execution request, etc., and feed back the processing result (e.g., simulation transaction data-just an example) to the terminal device.
It should be noted that the method for evaluating the pricing policy provided by the embodiment of the present invention is generally performed by the server 405, and accordingly, the system for evaluating the pricing policy is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The invention also provides the electronic equipment. The electronic device of the embodiment of the invention comprises: one or more processors; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the method for evaluating a pricing policy provided by the present invention.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use in implementing an electronic device of an embodiment of the present invention. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the computer system 500 are also stored. The CPU501, ROM 502, and RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, the processes described in the main step diagrams above may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the main step diagram. In the above-described embodiment, the computer program can be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the central processing unit 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present invention may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a modeling unit, an execution unit, and an evaluation unit. Where the names of these units do not in some cases constitute a limitation on the unit itself, for example, a modeling unit may also be described as a "unit that provides a simulation system to an execution unit".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to perform steps comprising: generating a user model corresponding to a real user and a commodity model corresponding to a real commodity according to the real service data, and establishing a simulation system by using the user model and the commodity model; in the simulation system, a user model determines whether to purchase a commodity model according to the selection probability of the user model on the commodity model; the selection probability is related to the current price of the commodity model; executing a first simulation process and a second simulation process in the simulation system, and respectively storing transaction data of the first simulation process and the second simulation process; the current price of any commodity model in the first simulation process is determined according to the initial price of the commodity model, and the current price of any commodity model in the second simulation process is determined according to the initial price of the commodity model and a pricing strategy to be evaluated; the trading totals of the first simulation process and the second simulation process are compared to evaluate the pricing strategy.
In the embodiment of the invention, a user model corresponding to a real user and a commodity model corresponding to a real commodity are generated according to real commodity information, transaction information, browsing information, evaluation information and the like, and a simulation system is established based on the user model and the commodity model and is used for respectively executing an original strategy and a pricing strategy so as to evaluate the pricing strategy. Therefore, the pricing strategy can be accurately evaluated on the premise of not influencing actual services, and the problems of difficult implementation, high risk, high cost and the like in the prior art are solved. In addition, in order to accurately simulate the real market, various parameters such as a expenditure willingness index, a brand preference index, a performance index of a commodity model, a brand value index and the like of the user model are extracted, a complete total utility value calculation formula is established so as to determine the selection probability of the commodity model by the user model, and a complex user behavior and interaction mechanism is realized in a simulation system, so that the reliability of the pricing strategy evaluation method is improved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (16)

1. A method for evaluating a pricing strategy, comprising:
generating a user model corresponding to a real user and a commodity model corresponding to a real commodity according to the real service data, and establishing a simulation system by using the user model and the commodity model; in the simulation system, a user model determines whether to purchase a commodity model according to the selection probability of the user model on the commodity model; the selection probability is related to the current price of the commodity model;
executing a first simulation process and a second simulation process in the simulation system, and respectively storing transaction data of the first simulation process and the second simulation process; the current price of any commodity model in the first simulation process is determined according to the initial price of the commodity model, and the current price of any commodity model in the second simulation process is determined according to the initial price of the commodity model and a pricing strategy to be evaluated; and
the trading totals of the first simulation process and the second simulation process are compared to evaluate the pricing strategy.
2. The method of claim 1, wherein the real goods are goods of the same category; any user model is provided with at least one of the following parameters: a spending willingness index, a brand preference index, a performance demand index; any commodity model is provided with at least one of the following parameters: performance index, brand value index, price sensitivity, brand sensitivity, performance sensitivity; wherein the content of the first and second substances,
the expenditure willingness index is determined according to the price of the real commodity purchased and/or browsed by the real user corresponding to the user model;
the brand preference index is determined according to the browsing times of the real users corresponding to the user model aiming at the real commodities of different brands;
the performance demand index is determined according to the performance index of the real commodity purchased and/or browsed by the real user corresponding to the user model;
the brand value index is determined according to the evaluation scores of real commodities with the commodity model brand; and
different commodity models are provided with the same price sensitivity, brand sensitivity and performance sensitivity.
3. The method of claim 2, wherein the building a simulation system using a user model and a commodity model comprises:
setting a simulation period, the number of user models in the current simulation period, a simulation step length, a price floating strategy and a replenishment strategy;
uniformly sampling three dimensions of a spending will index, a brand preference index and a performance demand index aiming at a user model generated according to real service data to obtain a user model of the current simulation period; and
determining the number of user models of the current simulation step length according to the Poisson distribution; and randomly sampling in the user model of the current simulation period according to the number to obtain the user model of the current simulation step length.
4. The method of claim 2, wherein the selection probability is determined by a total utility value of the commodity model to the user model; the total utility value is the sum of the price utility value, the brand utility value, the performance utility value and the inherent utility value of the commodity model to the user model; wherein the content of the first and second substances,
the price utility value is: the product of the price sensitivity and the quotient of the expenditure willingness index of the user model and the current price of the commodity model;
the brand utility value is: the product of a brand preference index of a user model for a commodity model, a brand value index of the commodity model and the brand sensitivity;
the performance utility values are: a product of a performance demand index of the user model, a performance index of the commodity model, and the performance sensitivity.
5. The method of claim 4, further comprising:
in the simulation system: if the sum of the selection probabilities of the user model to each commodity model is larger than a preset threshold value, randomly purchasing a commodity model according to the selection probabilities; and entering a waiting state if the sum of the selection probabilities of the user model to each commodity model is not greater than the threshold value.
6. The method of claim 3,
the current price of any commodity model in the first simulation process is determined according to the initial price, and the method specifically comprises the following steps: when the first simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the price floating strategy;
the current price of any commodity model in the second simulation process is determined according to the initial price and the pricing strategy to be evaluated, and the method specifically comprises the following steps: when the second simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the pricing strategy and the price floating strategy; wherein the pricing strategy adjusts the current price of the commodity model based on the transaction data in the second simulation process.
7. The method of any of claims 1-6, wherein the first simulation process and the second simulation process are simulated at the same time, and wherein the transaction total comprises: total sales, and/or total profit.
8. A pricing strategy evaluation system, comprising:
the modeling unit is used for generating a user model corresponding to a real user and a commodity model corresponding to a real commodity according to real service data, and establishing a simulation system by utilizing the user model and the commodity model; in the simulation system, a user model determines whether to purchase a commodity model according to the selection probability of the user model on the commodity model; the selection probability is related to the current price of the commodity model;
the execution unit is used for executing a first simulation process and a second simulation process in the simulation system and respectively storing the transaction data of the first simulation process and the second simulation process; the current price of any commodity model in the first simulation process is determined according to the initial price of the commodity model, and the current price of any commodity model in the second simulation process is determined according to the initial price of the commodity model and a pricing strategy to be evaluated; and
and the evaluation unit is used for comparing the transaction total of the first simulation process and the second simulation process so as to evaluate the pricing strategy.
9. The system of claim 8, wherein the real goods are goods of the same category; any user model is provided with at least one of the following parameters: a spending willingness index, a brand preference index, a performance demand index; any commodity model is provided with at least one of the following parameters: performance index, brand value index, price sensitivity, brand sensitivity, performance sensitivity; wherein the content of the first and second substances,
the expenditure willingness index is determined according to the price of the real commodity purchased and/or browsed by the real user corresponding to the user model;
the brand preference index is determined according to the browsing times of the real users corresponding to the user model aiming at the real commodities of different brands;
the performance demand index is determined according to the performance index of the real commodity purchased and/or browsed by the real user corresponding to the user model;
the brand value index is determined according to the evaluation scores of real commodities with the commodity model brand; and
different commodity models are provided with the same price sensitivity, brand sensitivity and performance sensitivity.
10. The system of claim 9, wherein the modeling unit is further configured to:
setting a simulation period, the number of user models in the current simulation period, a simulation step length, a price floating strategy and a replenishment strategy; uniformly sampling three dimensions of a spending will index, a brand preference index and a performance demand index aiming at a user model generated according to real service data to obtain a user model of the current simulation period; determining the number of user models of the current simulation step length according to the Poisson distribution; and randomly sampling in the user model of the current simulation period according to the number to obtain the user model of the current simulation step length.
11. The system of claim 9, wherein the selection probability is determined by a total utility value of the commodity model to the user model; the total utility value is the sum of the price utility value, the brand utility value, the performance utility value and the inherent utility value of the commodity model to the user model; wherein the content of the first and second substances,
the price utility value is: the product of the price sensitivity and the quotient of the expenditure willingness index of the user model and the current price of the commodity model;
the brand utility value is: the product of a brand preference index of a user model for a commodity model, a brand value index of the commodity model and the brand sensitivity;
the performance utility values are: a product of a performance demand index of the user model, a performance index of the commodity model, and the performance sensitivity.
12. The system of claim 11, wherein the modeling unit is further configured to implement:
in the simulation system: if the sum of the selection probabilities of the user model to each commodity model is larger than a preset threshold value, randomly purchasing a commodity model according to the selection probabilities; and entering a waiting state if the sum of the selection probabilities of the user model to each commodity model is not greater than the threshold value.
13. The system of claim 10, wherein the execution unit is further configured to implement:
when the first simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the price floating strategy; when the second simulation process is started, the current price of any commodity model is equal to the initial price of the commodity model; after starting, the current price of any commodity model is adjusted according to the pricing strategy and the price floating strategy; wherein the pricing strategy adjusts the current price of the commodity model based on the transaction data in the second simulation process.
14. The system of any of claims 8-13, wherein the first simulation process and the second simulation process are simulated at the same time, and wherein the transaction total comprises: total sales, and/or total profit.
15. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
16. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
CN201810891316.2A 2018-08-07 2018-08-07 Pricing strategy evaluation method and system Pending CN110826823A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810891316.2A CN110826823A (en) 2018-08-07 2018-08-07 Pricing strategy evaluation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810891316.2A CN110826823A (en) 2018-08-07 2018-08-07 Pricing strategy evaluation method and system

Publications (1)

Publication Number Publication Date
CN110826823A true CN110826823A (en) 2020-02-21

Family

ID=69533722

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810891316.2A Pending CN110826823A (en) 2018-08-07 2018-08-07 Pricing strategy evaluation method and system

Country Status (1)

Country Link
CN (1) CN110826823A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112529689A (en) * 2020-12-16 2021-03-19 北京逸风金科软件有限公司 Method and device for simulating bank risk pricing strategy
CN113034173A (en) * 2021-03-03 2021-06-25 北京电解智科技有限公司 Method and apparatus for generating information
CN112529689B (en) * 2020-12-16 2024-04-26 北京逸风金科软件有限公司 Simulation method and device for bank risk pricing strategy

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030187708A1 (en) * 2002-04-01 2003-10-02 Accenture Global Services Gmbh Simulation and optimization system for retail store performance
CN1826617A (en) * 2003-06-03 2006-08-30 波音公司 Systems, methods and computer program products for modeling demand, supply and associated profitability of a good
CN101777147A (en) * 2008-11-05 2010-07-14 埃森哲环球服务有限公司 Forecast modeling
CN105205701A (en) * 2015-09-22 2015-12-30 创点客（北京）科技有限公司 Network dynamic pricing method and system
CN106127531A (en) * 2016-07-14 2016-11-16 北京物思创想科技有限公司 The method and system of differentiation price are performed based on machine learning
CN107194725A (en) * 2017-05-19 2017-09-22 武汉弗赅科技有限公司 Merchandising different geographical pricing method and system
CN107451872A (en) * 2017-08-10 2017-12-08 中国民航信息网络股份有限公司 The management method and device of flight freight rate

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030187708A1 (en) * 2002-04-01 2003-10-02 Accenture Global Services Gmbh Simulation and optimization system for retail store performance
CN1826617A (en) * 2003-06-03 2006-08-30 波音公司 Systems, methods and computer program products for modeling demand, supply and associated profitability of a good
CN101777147A (en) * 2008-11-05 2010-07-14 埃森哲环球服务有限公司 Forecast modeling
CN105205701A (en) * 2015-09-22 2015-12-30 创点客（北京）科技有限公司 Network dynamic pricing method and system
CN106127531A (en) * 2016-07-14 2016-11-16 北京物思创想科技有限公司 The method and system of differentiation price are performed based on machine learning
CN107194725A (en) * 2017-05-19 2017-09-22 武汉弗赅科技有限公司 Merchandising different geographical pricing method and system
CN107451872A (en) * 2017-08-10 2017-12-08 中国民航信息网络股份有限公司 The management method and device of flight freight rate

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112529689A (en) * 2020-12-16 2021-03-19 北京逸风金科软件有限公司 Method and device for simulating bank risk pricing strategy
CN112529689B (en) * 2020-12-16 2024-04-26 北京逸风金科软件有限公司 Simulation method and device for bank risk pricing strategy
CN113034173A (en) * 2021-03-03 2021-06-25 北京电解智科技有限公司 Method and apparatus for generating information

Similar Documents

Publication Publication Date Title
CN107465741B (en) Information pushing method and device
US10776816B2 (en) System and method for building a targeted audience for an online advertising campaign
CN106897905B (en) Method and device for pushing information and electronic equipment
CN108985809A (en) Motivate method, apparatus, electronic equipment and the storage medium of push
CN103123712A (en) Method and system for monitoring network behavior data
CN109213936B (en) Commodity searching method and device
CN107517251B (en) Information pushing method and device
CN110348921B (en) Method and device for selecting store articles
WO2020221022A1 (en) Service object recommendation method
CN112215448A (en) Method and device for distributing customer service
JP2023546849A (en) Machine learning to predict, recommend, and buy and sell securities in currency markets
AU2019277353A1 (en) Electronic content based on neural networks
CN115578138A (en) Marketing method, marketing device, marketing medium and computing equipment
CN110555713A (en) method and device for determining sales prediction model
CN110866625A (en) Promotion index information generation method and device
CN111798261A (en) Information updating method and device
CN113034168A (en) Content item delivery method and device, computer equipment and storage medium
CN109978594B (en) Order processing method, device and medium
CN110555747A (en) method and device for determining target user
CN111680213A (en) Information recommendation method, data processing method and device
CN112287208B (en) User portrait generation method, device, electronic equipment and storage medium
CN110826823A (en) Pricing strategy evaluation method and system
WO2022156589A1 (en) Method and device for determining live broadcast click rate
CN114298825A (en) Method and device for extremely evaluating repayment volume
CN111784091A (en) Method and apparatus for processing information

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination