Power coefficient as a similarity measure for memory-based collaborative recommender systems
Power coefficient as a similarity measure for memory-based collaborative recommender systems
Mohammad Yahya H. Al-Shamri
2014 · DOI: 10.1016/j.eswa.2014.03.025
Expert systems with applications · 56 Citations
TLDR
This paper explores Jaccard and Dice coefficients for matching users of CRS and shows that the proposed variants outperform Pearson correlation coefficient and cosine similarity measure as they are the most common approaches for memory-based CRS.