Research On Personalized Recommendation Of Online Travel Industry Based On Implicit Feedback Data

With the rapid development of the Internet 020,the online travel industry has the problem of information overloaded.As the number and variety of tourism products became more and more,online travel users are difficult to find the products which they need quickly and efficiently.By means of using historical interest of users,Personalized recommendation system can solve the problem.It can help users to find their own favorite items in the complicated information.Recommended system is mainly used in e-commerce,film and video,music and other fields,which means the study of the online travel industry recommended system is very little at present.This article proposed a personalized recommendation model which combined with logistic regression model and collaborative filtering algorithm,which applied to the online travel websites.The model presents recommender system by using implicit feedback data.At first,it uses logistic regression model to apply the implicit feedback data of users.The data of users' browsing behavior is converted to users' degree of interest in items.And then Recommending for users which combine collaborative filtering recommendation algorithm with the characteristics of the online travel industry.This model is completely utilize implicit feedback to make up for the drawbacks of the less explicit feedback,which fully tap the user's browsing behavior and obtain the users' interest degree.Experiments of this article proved that this model can effectively get the users' interest to produce high-quality recommendations.