Abstract
Recommender systems have evolved as a major component of many businesses across various domains. Recommender systems help users making quick decisions by providing relevant information based on the past history of the user. This research work is focussed to enhance the performance of a recommender system by doing hyper parameter tuning and optimization techniques using Grid Search and Bayesian Optimization. The dataset consists of ratings of various users on the product. The surprise package of Python has been used to build the recommender system. A Collaborative System type recommender system is used to predict the products for a user. Various classifiers like Baseline Only, KNN Basic, SVD, NMF, and Co-Clustering were used. RMS E is used as a metric to determine the efficacy of the recommender system. The results show that Bayesian Optimization performed better than grid search in terms of RMSE values and also in the number of iterations required. Tuning the parameters improved the RMSE values to a major extent as compared to default parameters.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.