Recommender systems algorithm selection using machine learning

Pimenidis, Elias; Kapetanakis, Stelios; Polatidis, Nikolaos

Abstract

This article delivers a methodology for recommender system algorithm selection using a machine learning classifier. Initially, statistical data from real collaborative filtering recommender systems have been collected to form the basis for a synthetic dataset since a real meta dataset doesn't exist. Once the da-taset has been developed a classifier can be applied to predict which recom-mender system among a range of algorithms will predict better for a given da-taset. The experimental evaluation shows that tree-based approaches such as Decision Tree and Random Forest work well and provide results with high accuracy and precision. We can conclude that machine learning can be used along with a meta dataset comprised of statistical information in order to predict which rec-ommender system algorithm will provide better recommendations for similar da-tasets.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 22nd International Conference on Engineering Applications of Neural Networks (EANN 2021)
• Start Date: Jun 25, 2021
• End Date: Jun 27, 2021
• Acceptance Date: Apr 18, 2021
• Online Publication Date: Jul 1, 2021
• Publication Date: Jul 1, 2021
• Deposit Date: May 17, 2021
• Publicly Available Date: Jul 2, 2022
• Publisher: Springer
• Pages: 477-487
• Series Title: Proceedings of the International Neural Networks Society
• Series Number: 3
• Series ISSN: 2661-8141
• Book Title: Proceedings of the 22nd Engineering Applications of Neural Networks Conference
• ISBN: 9783030805678
• DOI: https://doi.org/10.1007/978-3-030-80568-5_39
• Keywords: Recommender Systems; Datasets; Meta recommender; Algorithm selection, Machine learning
• Public URL: https://uwe-repository.worktribe.com/output/7336949
• Publisher URL: https://www.springer.com/series/16268?detailsPage=titles