Sudden Death: A New Way to Compare Recommendation Diversification
arXiv:1908.00419v1
AI Analysis
This work tackles a methodological problem for researchers in recommendation systems, but it appears incremental as it focuses on refining comparison metrics rather than introducing a new paradigm.
The paper addresses issues in comparing recommendation list diversity in offline experiments and introduces the Sudden Death score as an improved method for these comparisons.
This paper describes problems with the current way we compare the diversity of different recommendation lists in offline experiments. We illustrate the problems with a case study. We propose the Sudden Death score as a new and better way of making these comparisons.