Research On Conversion Rate Improvement Of E-Commerce Platform Search Advertising

The conversion rate of search advertising in the e-commerce platform,as an indicator to measure the performance of the advertising conversion,comprehensively portrays the user's intention to purchase the advertising product from the perspectives of advertising creativity,product quality,and merchant quality.Increasing conversion rates,on the one hand,enables advertisers to match the users who are most likely to purchase their own products,and increase the return on investment(ROI)of advertisers;on the other hand,it allows users to quickly find the products with the strongest willingness to purchase,thus improve the user experience in the e-commerce platform.With the gradual maturity of the e-commerce industry,merchants and users have put forward higher requirements for search advertising conversion.Unfortunately,for search advertising,existing research focuses on exposure and click-through rates,and research on conversion rates is rarely involved.What are the factors affecting the conversion rate,and how to improve the conversion rate has become an urgent problem to be solved.In response to this situation,this paper has carried out related research on the conversion rate of e-commerce platform search advertisements,as follows:By establishing a machine learning model with a conversion rate target,after learning and learning with big data,the characteristics of the model dependence are analyzed to find out the influencing factors of the conversion rate.The results of data mining show that among the influencing factors of search advertising conversion rate,the rankings are the logistics service,product sales,consumer preferences,and the accuracy of the e-commerce platform query recommendation words.Mapping the influencing factors to the three stages of the ad conversion process,the direction of the search ad conversion rate is raised: In the first stage,the e-commerce platform should try to improve the accuracy of the query recommendation;in the second stage,the merchant should combine the consumer characteristics.Accurate advertising,such as considering when to post what content to what user's advertising;in the third stage,the business should improve the quality of advertising products and stores,such as the establishment of commodity prices,through the activities to expand the sales of goods,improve store logistics Service,etc.Among them,the first stage of query recommendation is the basis of the whole conversion process,and the only controllable factor of the platform in the three stages.Therefore,for the platform,the research should be mainly carried out to improve the conversion rate.Based on this,further research is conducted on the query recommendation.Analyze the process of shopping search in the e-commerce platform,construct the Markov decision model of the query recommendation process in actual shopping,and design the deep reinforcement learning algorithm of the solution model.Finally,the model is verified by the example.The experimental results show that after 359 rounds of trials After learning,the platform learns the optimal strategy,and does not select popular content in a certain decision process,which proves the effectiveness of the algorithm.Compared with the traditional query recommendation,the method has the characteristics of accurate,intelligent and real-time adaptation.Based on data mining,this paper introduces a supervised machine learning algorithm to explore the influencing factors of advertising commodity conversion rate.Compared with traditional regression analysis,the influencing factors are more comprehensive and the process is relatively simple and has certain reference significance.At the same time,the query recommendation process is summarized into a sequence decision problem,and a more intelligent query recommendation algorithm is designed,which can provide reference for the design of the e-commerce query recommendation system.