Personalized Recommendation Of Clothing Based On User Preference

With the rapid development of e-commerce,online shopping has become one of the main ways of shopping.On the one hand,there is too much information about online clothing,which may drown users in the mass clothing information,how to quickly select the clothing needed for users and improve the shopping efficiency is very important for businesses.On the other hand,users have their own preferences for clothing and pay attention to the personalized needs of clothing.Therefore,the research on the clothing personalized recommendation method is very important to improve the user's shopping efficiency and meet the user's personalized needs.In this paper,a personalized recommendation model of clothing based on user preference is proposed.The main contents of this model are as follows:(1)Choose a certain type of clothing to build clothing samples.(2)The user's evaluation table is obtained by using the projection technique to obtain the user preference selection of the sample clothing.(3)The BP neural network is used to excavate the preference information in the evaluation table,and the user's preference model is formed.(4)According to each user's preference model,the data of the clothing to be recommended is input into each user's preference model,and each user's preference for each item to be recommended is calculated.(5)Each user's preference for the recommended clothing is ranked,and each user is recommended for clothing that has a high degree of preference so as to realize the personalized recommendation of the clothing.On the basis of the above-mentioned personalized recommendation model of clothing,taking women's winter wool coat as an example,a personalized recommendation system of winter wool coat clothing is designed and implemented.The core function of this system is to use the BP neural network to mine the user's dynamic preference for women's winter woolen coat through the user's evaluation of the sample,and then recommend the winter woolen coat to the user through preference analysis.In order to verify the feasibility of the personalized recommendation model based on user preference,forty female university students from Soochow University conducted a verification experiment on the personalized recommendation system.The experimental results showed that forty subjects had a rating of seventy points or more and a large number of clothing for the system's recommended clothing,but only seventeen subjects rated the system's recommended clothing by ninety points or more,and the number of clothes was less.It shows that this method is feasible,but the accuracy of the recommendation needs to be improved.The recommendation based on BP algorithm is compared with the recommendation based on rough set algorithm proposed by Qiuyan Li,the experimental results show that the average evaluation value of the clothing recommended by the BP neural network is higher than the average evaluation value of the clothing recommended by Qiuyan Li based on the rough set algorithm.Therefore,the recommendation effect of the proposed method in this paper is better than that recommended by Qiuyan Li based on the rough set algorithm.