Comparative analysis of collaborative filtering recommender system algorithms for e-commerce

Collaborative recommender systems are information filtering systems that seek to predict a user’s rating or preference for an item. They play a vital role in various business use cases, such as personalized recommendations, item ranking and sorting, targeted marketing and promotions, content curation and catalog organization, and feedback analysis and quality control. When evaluating these systems, rating prediction metrics are commonly employed. Efficiency, including the prediction time, is another crucial aspect to consider. In this study, the performance of different algorithms was investigated. The study employed a dataset consisting of e-commerce product ratings and assessed the algorithms based on rating prediction metrics and efficiency. The results demonstrated that each algorithm had its own set of strengths and weaknesses. For the metric of Root Mean Squared Error (RMSE), the BaselineOnly algorithm achieved the lowest mean value. Regarding Mean Absolute Error (MAE), the Singular Value Decomposition with Positive Perturbations Singular Value Decomposition with Positive Perturbations (SVDPP) algorithm exhibited the lowest mean value; Mean Squared Error (MSE) also achieved the lowest mean value. Moreover, the BaselineOnly algorithm showcased superior performance with the lowest mean test times when considering efficiency. Researchers and practitioners can use the findings of this study to select the best algorithm for a particular application. Researchers can develop new algorithms that combine the strengths of different algorithms. Practitioners can also use the findings of this study to tune the parameters of existing algorithms.