Decision-making method and system for manufacturer pricing under multiple impact factors

Abstract

The invention belongs to the technical field of pricing decision making, and particularly relates to a manufacturer pricing decision making method and system under multiple influence factors, and the method comprehensively considers the social learning behaviors of consumers, the return freight insurance policy of an e-commerce platform and the cooperation mode between a manufacturer and the e-commerce platform. By collecting consumer social learning behavior data, e-commerce platform return freight insurance policy data and manufacturer product sales data, a pricing decision model including a manufacturer, an e-commerce platform and consumers is constructed. The model can derive an optimal pricing strategy combination and a sales strategy combination of a manufacturer, thereby helping the manufacturer to accurately position a target customer group in a proxy sales mode, and maximizing the potential profit of the manufacturer. According to the invention, a scientific pricing decision basis is provided for manufacturers, and the market competitiveness can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of pricing decision making, and in particular relates to a pricing decision making method and system for manufacturers under multiple influencing factors. Background Art

[0002] With the development of the Internet economy, product returns have become more frequent, and manufacturers and e-commerce platforms have begun to actively explore various solutions. Among them, the "social learning" phenomenon has gradually become an important research direction. Consumers will learn about product information through multiple channels before purchasing, such as the comment function of e-commerce platforms, professional reviews on social media, and user experience sharing. These multi-channel social learning information will eventually be aggregated into a powerful "signal" that affects consumers' purchasing decisions and manufacturers' pricing decisions.

[0003] At the same time, in order to reduce the return rate and increase consumers' willingness to buy, many manufacturers choose to cooperate with insurance companies to provide consumers with return freight insurance (RFI). This relaxed return policy greatly increases consumers' willingness to buy, but it also inevitably leads to an increase in the return rate, which further affects the manufacturer's pricing strategy.

[0004] Although the existing technology has made preliminary explorations into the pricing decision-making methods and systems for manufacturers under multiple influencing factors, there are still the following major defects:

[0005] 1. Lack of comprehensive consideration: Existing technical solutions often only focus on one or several influencing factors, but fail to comprehensively consider multiple influencing factors such as consumers' social learning behavior in multiple channels and return shipping insurance policies, resulting in pricing strategies that are not comprehensive and accurate.

[0006] 2. Limited model applicability: Most current decision-making models are based on specific assumptions and conditions and are difficult to adapt to the complex and changing market environment and consumer behavior. Especially in the agency sales model, the existing models have limitations in deriving the optimal pricing strategy combination for manufacturers when considering RFI policies. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for manufacturer pricing decision-making under multiple influencing factors to solve the problems raised in the background technology.

[0008] The present invention achieves the above-mentioned purpose through the following technical solutions:

[0009] In a first aspect, the present invention proposes a manufacturer pricing decision method under multiple influencing factors, comprising:

[0010] S1. Collect the data to be analyzed, including consumer social learning behavior data, e-commerce platform return freight insurance policy data, and manufacturer product sales data;

[0011] S2. constructing a pricing decision model based on the data to be analyzed and the first preset condition, and generating data to be updated based on the sales strategy data and the pricing strategy data according to the pricing decision model;

[0012] S3. Input the real-time acquired social learning behavior data and e-commerce platform return freight insurance policy data into the pricing decision model, and determine whether the data to be updated needs to be updated based on the output results of the pricing decision model. If necessary, update the data to be updated in real time to generate the optimal pricing strategy combination and the optimal sales strategy selection.

[0013] Furthermore, the S1 includes:

[0014] S101. Based on the social learning behavior of consumers, social learning signals are formed, consumers are divided into active consumers and passive consumers, and the satisfaction probability and signal accuracy of each type of consumers are obtained;

[0015] S102. Obtain three types of return freight insurance policy data provided by the e-commerce platform: the manufacturer does not provide freight insurance, the manufacturer purchases freight insurance, and the consumer purchases freight insurance, as well as the commission rate of the e-commerce platform;

[0016] S103. Obtain the manufacturer's product sales data, as well as the manufacturer's return loss, return freight insurance premium and freight compensation ratio under each return freight insurance policy.

[0017] Further, the S2 includes:

[0018] S201. Calculate the expected utility of consumers purchasing products based on their expected utility function, and use the expected utility as an influencing factor in determining consumers' purchasing decisions;

[0019] S202. Calculate the profit data of the manufacturer under different pricing strategies and sales strategies based on the manufacturer's profit function formula, and use the profit data as a factor affecting the manufacturer's decision;

[0020] S203. Update the posterior probability of consumer satisfaction with the product based on the Bayesian formula, and use the posterior probability as an influencing factor of social learning behavior on consumer purchase decisions;

[0021] S204. Based on the influencing factor, the data to be analyzed and the first preset condition, it is determined whether the manufacturer chooses a sales strategy of selling products only to positive consumers or selling products to both positive and negative consumers;

[0022] S205. Based on the social learning behavior data and the calculation results of the posterior probability, the manufacturer formulates an optimal pricing strategy combination for active consumers and passive consumers.

[0023] Furthermore, the first preset condition is: when the positive consumer is satisfied with the product or when the negative consumer is satisfied with the product, the prior probability is updated to the posterior probability.

[0024] Furthermore, the data to be updated includes:

[0025] Without considering social learning behavior, the optimal retail price, maximum sales volume and optimal profit of the manufacturer are solved according to the utility function and profit function;

[0026] When considering social learning behavior, the expected utility of consumers is updated according to the posterior probability, and the optimal pricing strategy combination of manufacturers under different return policies is solved respectively;

[0027] The optimal profits under the optimal pricing strategy combination are compared, and the optimal sales strategy choice for the manufacturer is determined by combining the return loss, freight insurance compensation ratio and signal accuracy factors.

[0028] Furthermore, the sales strategy data:

[0029] Strategy A: The manufacturer sells products only to motivated consumers;

[0030] Strategy B: The manufacturer sells products to both active and passive consumers.

[0031] Furthermore, the real-time updating of the data to be updated generates an optimal pricing strategy combination and an optimal sales strategy selection:

[0032] When the e-commerce platform does not provide return shipping insurance service, the manufacturer determines whether to implement Strategy A or Strategy B based on signal accuracy and return loss;

[0033] When the manufacturer purchases return freight insurance, the manufacturer is determined to implement Strategy A or Strategy B based on the signal accuracy, return loss, and return compensation ratio;

[0034] When consumers purchase return shipping insurance, the manufacturer determines whether to implement strategy A or strategy B based on signal accuracy, return loss, return compensation ratio, and return shipping insurance premium.

[0035] In a second aspect, the present invention proposes a manufacturer pricing decision system under multiple influencing factors, characterized in that it is applied to execute any of the above-mentioned pricing decision methods, and the system comprises:

[0036] The data collection module is used to collect data to be analyzed, including consumer social learning behavior data, e-commerce platform return freight insurance policy data, and manufacturer product sales data;

[0037] A model building module, used to build a pricing decision model based on the data to be analyzed and the first preset condition, and generate data to be updated based on the sales strategy data and the pricing strategy data according to the pricing decision model;

[0038] The strategy formulation module is used to input the real-time acquired social learning behavior data and the e-commerce platform return freight insurance policy data into the pricing decision model, and determine whether the data to be updated needs to be updated according to the output result of the pricing decision model. If necessary, the data to be updated is updated in real time to generate the optimal pricing strategy combination and the optimal sales strategy selection.

[0039] The beneficial effects of the present invention are:

[0040] 1. The decision-making method proposed in this invention constructs an accurate pricing decision model by comprehensively considering multiple influencing factors such as consumers' social learning behavior, return freight insurance policy, and e-commerce platform commissions. This model can simulate consumers' purchase decision-making process in different situations, thereby helping manufacturers to formulate the best pricing strategy in a complex and changing market environment. Compared with traditional pricing methods, this method can better reflect the actual market situation and improve the accuracy and effectiveness of pricing.

[0041] 2. The present invention also proposes how to determine the range of conditions for the manufacturer to implement strategy A or strategy B under different return policies based on signal accuracy, return loss, return compensation ratio, and return freight insurance. This innovative decision-making process enables manufacturers to flexibly adjust sales strategies according to the purchasing intentions and return risks of different consumers to maximize profits. At the same time, this method also emphasizes the positive impact of social learning behavior on manufacturers' pricing decisions, which helps manufacturers to gain an in-depth understanding of consumer demand and market dynamics and enhance their market competitiveness. By implementing the pricing decision-making method and system of this application, manufacturers can not only effectively reduce the return rate, but also achieve steady profit growth while ensuring consumer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flowchart of the pricing decision method in the present invention;

[0043] Figure 2 Schematic diagram of the process of step S1 in the pricing decision method of the present invention;

[0044] Figure 3 It is a flowchart of step S2 in the pricing decision method of the present invention. DETAILED DESCRIPTION

[0045] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.

[0046] Example 1

[0047] like Figure 1-3 As shown, this embodiment proposes a pricing decision method for manufacturers under multiple influencing factors. The method comprehensively considers the social learning behavior of consumers, the return shipping insurance policy of the e-commerce platform, and the product sales data of the manufacturer, aiming to help manufacturers formulate optimal pricing and sales strategies to maximize profits. The method includes the following steps:

[0048] S1. Collect data to be analyzed, including consumer social learning behavior data, e-commerce platform return shipping insurance policy data, and manufacturer product sales data.

[0049] Further preferably, S1 comprises:

[0050] S101. Collect consumer social learning behavior data: Based on consumers’ social learning behavior, form social learning signals, divide consumers into active consumers and passive consumers, and obtain and analyze the satisfaction probability and signal accuracy of each type of consumers. The satisfaction probability reflects the consumer’s satisfaction with the product after purchase, while the signal accuracy measures the accuracy of the social learning signal on the consumer’s purchase decision.

[0051] For example, consumers often learn about products through "social learning" before purchasing, and social learning information from various channels is finally summarized into "signal I". Consumers will judge whether the product meets their preferences based on signal I and make a purchase decision. If signal I encourages consumers to buy products, it is called a positive signal P; if signal I prevents consumers from buying products, it is called a negative signal N. Consumers can only judge whether signal I is correct after the product arrives. Assuming that the accuracy of signal I is signal accuracy θ, for satisfied consumers S, positive signal P is a correct signal, and negative signal N is a wrong signal, that is, Pr(I=P|T=S)=θ, Pr(I=N|T=S)=1-θ. For dissatisfied consumers U, positive signal P is a correct signal, and negative signal N is a wrong signal, that is, Pr(I=N|T=U)=θ, Pr(I=P|T=U)=1-θ. Consumers who receive positive signal P are defined as "positive consumers", and consumers who receive negative signal N are defined as "negative consumers".

[0052] The collection and analysis of the above social learning behavior data enables manufacturers to more accurately understand consumer preferences and needs, thereby formulating pricing strategies that are more in line with market demand. At the same time, by distinguishing between active and passive consumers, manufacturers can formulate differentiated sales strategies for different types of consumers and achieve precision marketing.

[0053] S102. Collect data on return freight insurance policies on e-commerce platforms: Obtain three types of return freight insurance policies provided by e-commerce platforms: the manufacturer does not provide freight insurance, the manufacturer purchases freight insurance, and the consumer purchases freight insurance, as well as the commission rate of the e-commerce platform. These policies directly affect consumers' willingness to buy and the cost of returns.

[0054] By analyzing the impact of different return shipping insurance policies on consumer purchase intention and return rate, manufacturers can formulate more reasonable return policies to reduce return losses and improve consumer satisfaction. In addition, considering the impact of e-commerce platform commission rates, manufacturers can optimize pricing strategies to maximize profits.

[0055] S103. Collect manufacturer product sales data: obtain key data such as product cost, sales price, historical sales volume, return rate, and manufacturer return loss and return freight and insurance premium information under various return situations. These data provide the basis for building a pricing decision model.

[0056] S2. constructing a pricing decision model based on the data to be analyzed and the first preset condition, and generating data to be updated based on the sales strategy data and the pricing strategy data according to the pricing decision model;

[0057] Further preferably, S2 comprises:

[0058] S201. Calculate the expected utility of consumers purchasing products based on their expected utility function, and use the expected utility as an influencing factor in determining consumers' purchasing decisions;

[0059] S202. Calculate the profit data of the manufacturer under different pricing strategies and sales strategies based on the manufacturer's profit function formula, and use the profit data as a factor affecting the manufacturer's decision;

[0060] S203. Update the posterior probability of consumer satisfaction with the product based on the Bayesian formula, and use the posterior probability as an influencing factor of social learning behavior on consumer purchase decisions;

[0061] S204. Based on the influencing factor, the data to be analyzed and the first preset condition, it is determined whether the manufacturer chooses a sales strategy of selling products only to positive consumers or selling products to both positive and negative consumers;

[0062] S205. Based on the social learning behavior data and the calculation results of the posterior probability, the manufacturer formulates an optimal pricing strategy combination for active consumers and passive consumers.

[0063] In this embodiment, the construction of the pricing decision model enables manufacturers to comprehensively consider multiple influencing factors and formulate the best pricing strategy and sales strategy. By simulating the consumer purchase decision process in different scenarios, manufacturers can predict sales, return rates and profit levels under different strategies, and thus select the best strategy combination.

[0064] In particular, when constructing a pricing decision model, the present invention calculates the expected utility of consumers purchasing products based on their expected utility function, and uses the expected utility as an influencing factor in determining consumers' purchasing decisions; at the same time, the profit data of manufacturers under different pricing strategies and sales strategies are calculated based on the manufacturer's profit function formula, and the profit data is used as an influencing factor in the manufacturer's decision. In addition, the present invention also updates the posterior probability of consumers' satisfaction with the product based on the Bayesian formula, and uses the posterior probability as an influencing factor in how social learning behavior affects consumers' purchasing decisions.

[0065] Further preferably, the first preset condition is: when the positive consumer is satisfied with the product or when the negative consumer is satisfied with the product, the prior probability is updated to the posterior probability.

[0066] Further preferably, the data to be updated includes:

[0067] Without considering social learning behavior, the optimal retail price, maximum sales volume and optimal profit of the manufacturer are solved according to the utility function and profit function;

[0068] When considering social learning behavior, the expected utility of consumers is updated according to the posterior probability, and the optimal pricing strategy combination of manufacturers under different return policies is solved respectively;

[0069] The optimal profits under the optimal pricing strategy combination are compared, and the optimal sales strategy choice for the manufacturer is determined by combining the return loss, freight insurance compensation ratio and signal accuracy factors.

[0070] S3. Input the real-time acquired social learning behavior data and e-commerce platform return freight insurance policy data into the pricing decision model, and determine whether the data to be updated needs to be updated based on the output results of the pricing decision model. If necessary, update the data to be updated in real time to generate the optimal pricing strategy combination and the optimal sales strategy selection.

[0071] Further preferably, the sales strategy data:

[0072] Strategy A: The manufacturer sells products only to motivated consumers;

[0073] Strategy B: The manufacturer sells products to both active and passive consumers.

[0074] Further preferably, the real-time updating of the data to be updated generates an optimal pricing strategy combination and an optimal sales strategy selection:

[0075] When the e-commerce platform does not provide return shipping insurance service, the manufacturer determines whether to implement Strategy A or Strategy B based on signal accuracy and return loss;

[0076] When the manufacturer purchases return freight insurance, the manufacturer is determined to implement Strategy A or Strategy B based on the signal accuracy, return loss, and return compensation ratio;

[0077] When consumers purchase return shipping insurance, the manufacturer determines whether to implement strategy A or strategy B based on signal accuracy, return loss, return compensation ratio, and return shipping insurance premium.

[0078] Strategy formulation and analysis outputs enable manufacturers to flexibly adjust pricing and sales strategies according to changes in market environment and consumer behavior. By comparing indicators such as profit levels, sales volume and return rates under different strategies, manufacturers can evaluate the pros and cons of each strategy and select the optimal strategy combination to maximize profits.

[0079] More specifically, the specific description of the above conditions is as follows:

[0080] (1) When the e-commerce platform does not provide return shipping insurance (i.e. the manufacturer does not provide shipping insurance):

[0081] Manufacturers need to determine their sales strategies based on signal accuracy and return losses. Signal accuracy reflects the accuracy of social learning signals on consumer purchase decisions, while return losses refer to the losses incurred by manufacturers in processing returns so that they can be resold.

[0082] When the signal accuracy is high and the return loss is small, the manufacturer tends to implement strategy A, that is, selling products only to motivated consumers. This is because high signal accuracy means that motivated consumers are more likely to keep the product, while small return losses reduce the manufacturer's risk.

[0083] When the signal accuracy is low or the return loss is large, the manufacturer is more inclined to implement strategy B, that is, selling products to both positive and negative consumers. This is because low signal accuracy makes it difficult for manufacturers to accurately distinguish consumer types, while large return losses require manufacturers to spread the risk by expanding the sales range.

[0084] (2) When purchasing return shipping insurance from the manufacturer:

[0085] In addition to considering signal accuracy and return losses, manufacturers also need to consider the return compensation ratio. The return compensation ratio is the compensation ratio that manufacturers can obtain when the product is returned after purchasing freight insurance for consumers.

[0086] When the signal accuracy is high, the return loss is moderate, and the return compensation ratio is high, the manufacturer tends to implement strategy A. This is because high signal accuracy and moderate return losses make the manufacturer more confident in sales to active consumers, while a high return compensation ratio reduces the manufacturer's return costs.

[0087] When the signal accuracy is low, the return loss is large, or the return compensation ratio is low, the manufacturer is more inclined to implement strategy B. This is because low signal accuracy and large return losses make it difficult for manufacturers to accurately predict sales results, while low return compensation ratios increase the manufacturer's return costs.

[0088] (3) When consumers purchase return shipping insurance:

[0089] Manufacturers also need to factor in return shipping insurance, which is the fee consumers pay to purchase shipping insurance.

[0090] When signal accuracy, return loss, return compensation ratio, and return freight insurance premium are all at moderate levels, manufacturers can flexibly choose Strategy A or Strategy B according to market conditions.

[0091] When one of these factors deviates from the moderate level, manufacturers need to make trade-offs and decisions based on the specific situation. For example, when the return shipping insurance premium is high, the manufacturer may tend to implement strategy A to reduce the additional costs incurred by returns.

[0092] According to the above embodiments, the present invention provides an accurate pricing decision model for manufacturers by comprehensively considering multiple influencing factors such as consumers' social learning behavior, return freight insurance policy, and e-commerce platform commissions. The model can simulate the purchase decision process of consumers in different situations, thereby helping manufacturers to formulate optimal pricing and sales strategies in a complex and changing market environment. Compared with traditional pricing methods, this method can better reflect the actual market situation and improve the accuracy and effectiveness of pricing.

[0093] Based on the same inventive concept, this embodiment also proposes a manufacturer pricing decision system under multiple influencing factors, which is applied to execute the above pricing decision method. The system includes:

[0094] The data collection module is used to collect data to be analyzed, including consumer social learning behavior data, e-commerce platform return freight insurance policy data, and manufacturer product sales data;

[0095] A model building module, used to build a pricing decision model based on the data to be analyzed and the first preset condition, and generate data to be updated based on the sales strategy data and the pricing strategy data according to the pricing decision model;

[0096] The strategy formulation module is used to input the real-time acquired social learning behavior data and the e-commerce platform return freight insurance policy data into the pricing decision model, and determine whether the data to be updated needs to be updated according to the output result of the pricing decision model. If necessary, the data to be updated is updated in real time to generate the optimal pricing strategy combination and the optimal sales strategy selection.

[0097] It should be noted here that each module in the above-mentioned pricing decision system corresponds to steps S1 to S3 in implementing the above-mentioned pricing decision method, and the instances and application scenarios implemented by multiple modules are the same as those of the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0098] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of the manufacturer pricing decision method under multiple influencing factors are implemented.

[0099] In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the manufacturer pricing decision method under multiple influencing factors in the above embodiment.

[0100] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present invention are generated.

[0101] The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0102] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A pricing decision method for manufacturers under multiple influencing factors, characterized in that: include: S1. Collect the data to be analyzed, including consumer social learning behavior data, e-commerce platform return freight insurance policy data, and manufacturer product sales data; S2. constructing a pricing decision model based on the data to be analyzed and the first preset condition, and generating data to be updated based on the sales strategy data and the pricing strategy data according to the pricing decision model; S3. Input the real-time acquired social learning behavior data and e-commerce platform return freight insurance policy data into the pricing decision model, and determine whether the data to be updated needs to be updated based on the output results of the pricing decision model. If necessary, update the data to be updated in real time to generate the optimal pricing strategy combination and the optimal sales strategy selection.

2. The method for manufacturer pricing decision under multiple influencing factors according to claim 1 is characterized by: The S1 includes: S101. Based on the social learning behavior of consumers, social learning signals are formed, consumers are divided into active consumers and passive consumers, and the satisfaction probability and signal accuracy of each type of consumers are obtained; S102. Obtain three types of return freight insurance policy data provided by the e-commerce platform: the manufacturer does not provide freight insurance, the manufacturer purchases freight insurance, and the consumer purchases freight insurance, as well as the commission rate of the e-commerce platform; S103. Obtain the manufacturer's product sales data, as well as the manufacturer's return loss, return freight insurance premium and freight compensation ratio under each return freight insurance policy.

3. The method for manufacturer pricing decision under multiple influencing factors according to claim 1 is characterized by: The S2 includes: S201. Calculate the expected utility of consumers purchasing products based on their expected utility function, and use the expected utility as an influencing factor in determining consumers' purchasing decisions; S202. Calculate the profit data of the manufacturer under different pricing strategies and sales strategies based on the manufacturer's profit function formula, and use the profit data as a factor affecting the manufacturer's decision; S203. Update the posterior probability of consumer satisfaction with the product based on the Bayesian formula, and use the posterior probability as an influencing factor of social learning behavior on consumer purchase decisions; S204. Based on the influencing factor, the data to be analyzed and the first preset condition, it is determined whether the manufacturer chooses a sales strategy of selling products only to positive consumers or selling products to both positive and negative consumers; S205. Based on the social learning behavior data and the calculation results of the posterior probability, the manufacturer formulates an optimal pricing strategy combination for active consumers and passive consumers.

4. The method for manufacturer pricing decision under multiple influencing factors according to claim 3 is characterized by: The first preset condition is: when the positive consumer is satisfied with the product or when the negative consumer is satisfied with the product, the prior probability is updated to the posterior probability.

5. The method for manufacturer pricing decision under multiple influencing factors according to claim 3 is characterized by: The data to be updated includes: Without considering social learning behavior, the optimal retail price, maximum sales volume and optimal profit of the manufacturer are solved according to the utility function and profit function; When considering social learning behavior, the expected utility of consumers is updated according to the posterior probability, and the optimal pricing strategy combination of manufacturers under different return policies is solved respectively; The optimal profits under the optimal pricing strategy combination are compared, and the optimal sales strategy choice for the manufacturer is determined by combining the return loss, freight insurance compensation ratio and signal accuracy factors.

6. The method for manufacturer pricing decision under multiple influencing factors according to claim 5 is characterized by: The sales strategy data: Strategy A: The manufacturer sells products only to motivated consumers; Strategy B: The manufacturer sells products to both active and passive consumers.

7. The method for manufacturer pricing decision under multiple influencing factors according to claim 6 is characterized by: The optimal pricing strategy combination and the optimal sales strategy selection are generated after the data to be updated is updated in real time: When the e-commerce platform does not provide return shipping insurance service, the manufacturer determines whether to implement Strategy A or Strategy B based on signal accuracy and return loss; When the manufacturer purchases return freight insurance, the manufacturer is determined to implement Strategy A or Strategy B based on the signal accuracy, return loss, and return compensation ratio; When consumers purchase return shipping insurance, the manufacturer determines whether to implement strategy A or strategy B based on signal accuracy, return loss, return compensation ratio, and return shipping insurance premium.

8. A manufacturer pricing decision system under multiple influencing factors, characterized by: Applied to executing the pricing decision method according to any one of claims 1 to 7, the system comprises: The data collection module is used to collect data to be analyzed, including consumer social learning behavior data, e-commerce platform return freight insurance policy data, and manufacturer product sales data; A model building module, used to build a pricing decision model based on the data to be analyzed and the first preset condition, and generate data to be updated based on the sales strategy data and the pricing strategy data according to the pricing decision model; The strategy formulation module is used to input the real-time acquired social learning behavior data and the e-commerce platform return freight insurance policy data into the pricing decision model, and determine whether the data to be updated needs to be updated according to the output result of the pricing decision model. If necessary, the data to be updated is updated in real time to generate the optimal pricing strategy combination and the optimal sales strategy selection.

Images