Fusion of personalized recommendation model based on user's interest drifting
Guoping Tan · Jisuanji gongcheng yu sheji · 2013
With the development of mobile Internet,a large number of applications swarm into application stores.Personalized service and recommendation are effective methods to solve the problem —application-mazing.Aimed at some Telecom's IGame application platform and other similar application stores,a fused personalized recommendation solution is proposed.Through analyzing users' operation logs,the user's interest preference model is generated.At the same time,time factor which reflects the drift of users' interest is introduced.At last,the method based on user's preference analysis recommendation is combined with the item based collaborative filtering algorithm.The experimental results show that our model can avoid the shortage of above two algorithms and keep their advantages.The system's comprehensive performance of personalized recommendation is improved effectively.