Case Recommender: A Recommender Framework

• Arthur F. da Costa USP
• Marcelo G. Manzato USP

Abstract

Case Recommender is a Python implementation of a number of popular content-based and collaborative recommendation algorithms which use implicit and explicit feedback. The framework aims to provide a rich set of components from which developers can construct a customized recommender system. One differential of the framework is the possibility to combine multiple recommenders in a post-processing ensemble approach to produce more accurate results. Case Recommender can be used for rating prediction and item recommendation tasks, and it includes different metrics and procedures for validation and evaluation.

Keywords: Recommender Systems; Framework