AI-Powered Movie Recommendation System

This paper presents a comprehensive Artificial Intelligence (AI)-powered Hybrid Movie Recommendation System designed to enhance the accuracy, scalability, and relevance of movie suggestions. The system integrates two major AI-driven approaches: Collaborative Filtering and Content-Based Filtering. Using the MovieLens dataset, the model employs TF- IDF vectorization, cosine similarity, and a hybrid ranking strategy to combine both rating- based and content-based insights. This hybrid system addresses common limitations such as cold-start problems, sparsity of rating matrices, and limited content representation. Empirical results demonstrate that the hybrid system provides more accurate and diverse recommendations compared to traditional single-method approaches. The system is easy to implement, scalable, and suitable for real- world applications in OTT platforms, entertainment services, and personalized content delivery systems.