<![CDATA[This study aims to improve the accuracy of movie rating predictions by applying and combining collaborative filtering and machine learning techniques in a hybrid recommender system. The research utilizes the MovieLens dataset to implement two distinct approaches: the Alternating Least Squares (ALS) matrix factorization model and the CatBoost gradient boosting model. The ALS model is trained to capture latent user–item interactions, while CatBoost leverages nonlinear relationships using user and item features. A simple hybrid strategy averages the predictions from both models to evaluate potential performance gains. Experimental results show that the hybrid approach achieves lower error metrics compared to either model individually, with Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values of 0.828 and 0.666, respectively. This demonstrates that combining latent factor models with tree-based learning can effectively reduce prediction errors by exploiting complementary strengths. The novelty of this research lies in its efficient yet effective hybridization strategy that improves recommendation quality without complex ensembling techniques. The findings suggest that even lightweight model fusion can significantly enhance predictive accuracy in recommender systems and may be adapted for other domains where combining linear and nonlinear modeling is beneficial. This research contributes to the field of Informatics and Computer Science by demonstrating that a lightweight hybridization of latent factor models and tree-based learning can significantly improve recommender system accuracy while offering practical implications for real-world digital applications.]]>
Copyrights © 2025
