SIGNATURE WORK
CONFERENCE & EXHIBITION 2022

As the world enters the era of big data, the data generated by the film industry shows an exponential growth. The increasing number of users and films on the film rating platform makes it increasingly difficult for users to find the films that they are really interested in. Among the various film data, how to associate films with users and help them obtain useful information is a big problem we face. With the deepening of research worldwide, a personalized recommendation system can be customized according to the demand. Different from most studies on individual users, this paper uses optimized profile strategies, matrix factorization such as singular value decomposition algorithm, established a group-based film recommendation system, and provide group recommendations while still work as an individual recommendation system if needed. This paper aims to cover the research gap between individual and group recommendation, provides the system which is able to provide good accuracy based on the feedback from individual ratings, fulfill the most requirements and hopefully can be applied to real-world scenario in the future.