TV Program Recommender System Using Viewing Time Patterns

Abstract As a number of TV programs broadcast today, researches about TV program recommender system have been studied and many researchers have been studying recommende r system to produce recommendation with high accuracy. Recommender system recommends TV program to user by using metadata like genre, plot or calculating users’ preferences about TV programs. In th is paper, we propose a new TV program Collaborative Filtering Recommender System that exploits viewin g time pattern like viewing ratio, relation with finish time and recently viewing history to calculate prefe rence for high-quality of recommendation. To verify usefulness of our research, we also compare our method wh ich utilizes viewing time patterns and baseline which simply recommends TV program of user's most freq uently watched channel. Through this ex-periments, we show that our method very effectively works and r ecommendation performance increases.Key Words : TV Program, Recommender System, Viewing time Patterns, Collaborative Filtering Received: Mar. 22, 2015Revised : Apr. 5, 2015Accepted: Sep. 15, 2015