A Novel Movie Recommendation System Based on Collaborative Filtering and Neural Networks
Movie recommendation is one of the most common recommendation systems, and the related technologies for recommendation are constantly improving. It has evolved from traditional statistical analysis to collaborative filtering and machine learning today. This paper aims to find a set of criteria that are practical, reasonable, and accurate in using existing recommendation systems. We compare some techniques and tools and conduct experiments for popular tools currently used, especially Scikit-learn and TensorFlow. The experiments focus on the comparison of the advantages, error measure, and process time of these tools. From the experimental results, we further propose a novel recommendation system, based on collaborative filtering and neural network, which maintains lower error measure.
This research was partly supported by the Ministry of Science and Technology, Taiwan, under grant number MOST 107 - 2221 - E - 029 - 005 - MY3.
- 1.Weng, S.-S., Lee, C.-H.: Integration of content-based approach and hybrid collaborative filtering for movie recommendation. In: BAI 2013 International Conference on Business and Information (2013)Google Scholar
- 2.Mustafa, N., Ibrahim, A.O.: Collaborative filtering: techniques and applications. In: 2017 International Conference on Communication, Control, Computing and Electronics Engineering (ICCCCEE) (2017)Google Scholar
- 3.Luo, T., Chen, S., Xu, G., Zhou, J.: Collaborative filtering. In: Trust-based Collective View Prediction, pp. 25–51 (2013)Google Scholar
- 6.Abadi, M., Barham, P., et al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation, pp. 264–283 (2016)Google Scholar
- 7.MovieLens Recommender System. https://github.com/chengstone/movie_recommender