Ensemble Boost: Greedy Selection for Superior Recommender Systems

TL;DR

The paper tackles information overload in recommender systems by introducing a Weighted Ranking ensemble built with Forward Greedy Ensemble Selection over ten diverse models. By weighting each model's scores with its validation $NDCG$ and aggregating top-N lists per user, the approach constructs ensembles that surpass the best individual models across five datasets, achieving notable gains (up to $NDCG$ improvements around 30% on $NDCG@20$). The findings demonstrate the robustness of greedy ensemble selection in recommender contexts and highlight substantial performance gains alongside computational costs. This work advances practical ensemble strategies for recommender systems, offering a scalable pathway to more accurate and diverse recommendations in real-world platforms.

Abstract

Ensemble techniques have demonstrated remarkable success in improving predictive performance across various domains by aggregating predictions from multiple models [1]. In the realm of recommender systems, this research explores the application of ensemble technique to enhance recommendation quality. Specifically, we propose a novel approach to combine top-k recommendations from ten diverse recommendation models resulting in superior top-n recommendations using this novel ensemble technique. Our method leverages a Greedy Ensemble Selection(GES) strategy, effectively harnessing the collective intelligence of multiple models. We conduct experiments on five distinct datasets to evaluate the effectiveness of our approach. Evaluation across five folds using the NDCG metric reveals significant improvements in recommendation accuracy across all datasets compared to single best performing model. Furthermore, comprehensive comparisons against existing models underscore the efficacy of our ensemble approach in enhancing recommendation quality. Our ensemble approach yielded an average improvement of 21.67% across different NDCG@N metrics and the five datasets, compared to single best model. The popularity recommendation model serves as the baseline for comparison. This research contributes to the advancement of ensemble-based recommender systems, offering insights into the potential of combining diverse recommendation strategies to enhance user experience and satisfaction. By presenting a novel approach and demonstrating its superiority over existing methods, we aim to inspire further exploration and innovation in this domain.

Figures (5)

• Figure 1: Steps to generate ensembled list of recommendations of each user
• Figure 2: Example of Forward Greedy Ensemble Selection on four models
• Figure 3: "NDCG(@5) Score vs k" across different datasets
• Figure 4: "NDCG(@10) Score vs k" across different datasets
• Figure 5: "NDCG(@20) Score vs k" across different datasets