Evaluating Models For Movie Recommendation: A Comparative Study To Enhance User Experience

Authors: Nikil Kumar, Uttam, Priya Chauhan, Anurag Gupta

Abstract: In the rapidly growing personal entertainment space, providing great video recommendations on a wide range of topics is vital to amplify customer satisfaction. This study compares various machine learning algorithms to evaluate their effectiveness in predicting video preferences based on user behavior and historical data. The analysis uses techniques like user-based filtering, item- based filtering, hybrid models, decision trees, and neural networks. The methods were evaluated using performance metrics including metrics like accuracy, sensitivity, F1 measure, and root mean squared deviation (RMSD). The results show that there is a significant difference between the algorithms in terms of accuracy and computational efficiency, with the hybrid model outperforming other models in capturing user preferences. Artificial neural networks also show potential in managing customer interactions, although they require more investment. This research provides a good understanding of the capabilities and limitations of different machine learning methods, laying the foundation for future developments and practical applications of recommendations.