Keywords
Recommender Systems, Collaborative Filtering, Matrix Factorization, MovieLens, Cosine Similarity, RMSE, SVD, User-Item Interactions, Latent Factors, Personalization
Abstract
This study presents a comparative analysis of Collaborative Filtering and Matrix Factorization techniques applied to the MovieLens 100K dataset for building recommender systems. Collaborative Filtering, grounded in user similarity, and Matrix Factorization, which uncovers latent factors, are both critical in predicting user preferences. Our research involves the implementation and evaluation of these methods to determine their effectiveness in predicting movie ratings. Through meticulous experimentation, we optimized the models and assessed their performance using the Root Mean Square Error (RMSE) metric. Results indicate that both methods are robust, with Collaborative Filtering achieving a slightly better RMSE. This paper contributes to the field by providing insights into the accuracy of these prevalent recommender system algorithms and their practical application in enhancing user experience on movie platforms.
Semester
2026
Course Name
STA 6367 Data Science 2
Instructor Name
Dr. Rui Xie
College
College of Sciences
STARS Citation
Issoufou Anaroua, Amina; Alipour Yengejeh, Amir; and Agbemade, Emil, "Comparative Analysis of Collaborative Filtering and Matrix Factorization Techniques in MovieLens Recommender Systems" (2026). Data Science and Data Mining. 55.
https://stars.library.ucf.edu/data-science-mining/55
Included in
Accessibility Statement
This item was created or digitized prior to April 24, 2027, or is a reproduction of legacy media created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. In accordance with the ADA Title II Final Rule, the University Libraries provides accessible versions of archival materials upon request. To request an accommodation for this item, please submit an accessibility request form.