A Comprehensive Survey on Movie Recommendation Systems

Internet technology has occupied an important part of human lives. Users often face the problem of the available excessive information. Recommandation system (RS) are deployed to help users cope up with the information explosion. RS is mostly used in digital entertainment, such as Netflix, prime video, and IMDB, and e-commerce portals such as Amazon, Flipkart, and eBay. The two traditional methods namely, collaborative filtering (CF) and content-based approaches consist of few limitations individually. However, any hybrid system, which utilizes the advantage of both the systems to leverage better results. Some fundamental issues faced by movie recommendation systems such as scalability, cold start problem, data sparsity and practical usage feedback and verification based on real implementation are still neglected. Other issues that require significant research attention are accuracy and time complexity problem, which could make RS, a bad candidate for real-world recommendation systems. This literature survey aims to consolidate and structurally categorize all the major drawbacks present in the most common and popular commercial movie recommendation systems.