Recommender Systems

Link to Full Report (PDF) Contributions: Development of the RainFM hybrid model, integrating matrix factorization, neural networks, and Bayesian inference. Implementation of a stratified data grouping strategy to enhance predictive accuracy. Extensive evaluation of baseline and hybrid models, including SVD, ALS, GMF, MLP, and BFM. Authors: Rainer Feichtinger, Rongxing Liu, Justin Lo, Ruben Schenk Institution: ETH Zurich, Computational Intelligence Lab Overview The RainFM project addresses the challenge of enhancing predictive accuracy in recommender systems by combining multiple collaborative filtering (CF) strategies. By stratifying the dataset based on statistical properties and applying distinct models to each subset, RainFM demonstrates improved accuracy in item recommendation over conventional approaches. ...