Diversifying Music Recommendations
arXiv:1810.01482v115 citations
Originality Incremental advance
AI Analysis
This addresses the problem of user satisfaction in music streaming services, though it appears incremental as it builds on existing diversification techniques.
The paper tackled the problem of improving music recommendation diversity by comparing submodular and Jaccard methods on Amazon Music data, finding that the submodular approach significantly enhanced recommendation quality and user engagement.
We compare submodular and Jaccard methods to diversify Amazon Music recommendations. Submodularity significantly improves recommendation quality and user engagement. Unlike the Jaccard method, our submodular approach incorporates item relevance score within its optimization function, and produces a relevant and uniformly diverse set.