<![CDATA[With the increasing prevalence of digital platforms, recommender systems play a crucial role in personalizing user experiences. However, selecting an appropriate recommender system algorithm remains challenging due to inconsistent evaluation procedures and limited comparative studies that simultaneously address accuracy, efficiency, and architectural extensibility. This study compares nine recommender system algorithms, including traditional collaborative filtering (SVD, SVD++, KNN, NMF, SlopeOne), content-based filtering, hybrid approach, and deep learning autoencoder technique using MovieLens-1M and MovieLens-100K dataset. The hybrid approach achieved the best accuracy (RMSE 0.6865), followed by SVD++ and SVD (RMSE 0.8660 and 0.8729). Autoencoder demonstrated moderate performance (RMSE 0.9961) with 14% accuracy gap from SVD. Computational efficiency varied greatly, from 0.29 seconds for content-based methods to 3,470.73 seconds for SVD++. Cross-dataset validation of collaborative filtering methods confirmed consistency across datasets. Beyond accuracy metrics, architectural analysis identified autoencoder's extensibility advantage for integrating heterogeneous data sources, an important consideration for systems requiring multimodal capabilities. The findings provide empirical insights for method selection based on system priorities such as accuracy, efficiency, and architectural flexibility for multimodal integration.]]>
Copyrights © 2026
