Movie Recommendation Based System Using Time Series Data

Abstract

Finding the right movie from a wide selection can be difficult, leading to frustration and wasted time. Recommendation systems offer a solution by providing personalized movie recommendations based on users' interests and preferences. These systems use data analytics, machine learning algorithms and temporal analysis techniques to understand user behavior and provide accurate recommendations. Collaborative filtering algorithms identify similarities between users or movies, while content-based filtering separates movie features based on user preferences. Time series analysis methods collect temporal patterns for dynamic recommendations. The results of the literature review support the effectiveness of movie recommendation systems based on time series data, showing their ability to provide accurate recommendations despite changing information and changing preferences. Real-time data collection improves system efficiency. Overall, the proposed solution aims to improve the movie selection process, save users time and effort, and at the same time improve the movie viewing experience.