Research On Platform Recommendation Under Consumer Perception And Network Effect

The popularity of the Internet allows people to obtain goods and services they need through fingertip click.However,with the growing maturity of retail platforms,massive collection of goods makes consumers dazzled,resulting in information overload,which adversely affects their shopping experience on the platform.In order to solve this problem,most of the platforms use a recommendation system to personalize the recommendation of consumers.This service allows consumers to save a lot of time and energy on the selection of goods,and also helps them to create demand for their interests.In many fields this technical service has become an indispensable service in helping platform businesses to improve the conversion rate of purchases.In order to seize the market for customer,platform use various analytical techniques to compete to improve the recommend mechanism.Since users’ satisfaction is closely related to the scale of the network,how can we ignore the impact of the network effects of both parties on the technology investment and pricing of e-commerce platforms? In the era of consumer-oriented economy,different consumers will have different perceptions of the utility of the same goods or services.How should the platform react to this phenomenon? The degree of technical input determines the accuracy that platform push can achieve,and the accuracy will affect the perception of the bilateral users of the platform.So,how to determine the technology input talent to maximize the benefits?In view of the above considerations,this paper is based on the previous scholars’ research on platform decision-making,constructs the corresponding model under the research background.This paper will further considers the network effect and consumer perception into the platform of technical input and pricing research.The platform profit model is constructed to solve the platform push decision that the platform achieves the optimal level under the influence of different utility perceptions and different network externalities of the users of the platform.Then,exploring the impact of variables on platform decisions,and performing numerical simulations to visualize the results.The main results obtained are as follows:(1)Consumer does not necessarily have a complete perception of the platform’s accurate push service.Because of the heterogeneity,the consumer’s perception has a threshold.The technology investment and pricing strategy of the platform needs to analyze the scope of the consumer’s perceived acceptance level.When the consumer is at a lower or higher level of perceived acceptance,in order to ensure the optimal return of the platform,the push accuracy can be appropriately increased or decreased.(2)The cross-network externality between users on the platform has a positive impact on the platform’s optimal technology input level and optimal pricing.The positive network effect between consumers is also conducive to the improvement of platform revenue.Both negative network effects between consumers and negative network effects between merchants can have a negative impact on platform decisions and revenue.So,the platform should be supplemented by other welfare means for users of both sides to expand the positive impact and reduce the negative effect,so as to help precise recommendation service to play its best role.(3)The marginal cost of the technology investment of the platform has a restrictive effect on the platform decision.When the technology development cost is too high to be compensated from the investment income,even if consumers still have a large perceived acceptance space,the platform should stop the continuous investment of technology to maintain the current level to ensure maximum benefits.