On the discriminative power of Hyper-parameters in Cross-Validation and how to choose them

TL;DR

This paper investigates how hyper-parameters influence model performance and evaluation metrics in cross-validation, revealing the importance of parameter selection and its impact on accuracy and novelty in recommender systems.

Contribution

It provides an extensive analysis of hyper-parameters' discriminative power in cross-validation, highlighting the potential to focus on key parameters for better model tuning.

Findings

Hyper-parameters significantly affect accuracy and novelty metrics.

Certain parameters have higher discriminative power in model evaluation.

Focusing on a subset of parameters can be sufficient for effective tuning.

Abstract

Hyper-parameters tuning is a crucial task to make a model perform at its best. However, despite the well-established methodologies, some aspects of the tuning remain unexplored. As an example, it may affect not just accuracy but also novelty as well as it may depend on the adopted dataset. Moreover, sometimes it could be sufficient to concentrate on a single parameter only (or a few of them) instead of their overall set. In this paper we report on our investigation on hyper-parameters tuning by performing an extensive 10-Folds Cross-Validation on MovieLens and Amazon Movies for three well-known baselines: User-kNN, Item-kNN, BPR-MF. We adopted a grid search strategy considering approximately 15 values for each parameter, and we then evaluated each combination of parameters in terms of accuracy and novelty. We investigated the discriminative power of nDCG, Precision, Recall, MRR, EFD, EPC, and, finally, we analyzed the role of parameters on model evaluation for Cross-Validation.