Reproduce “Personalized Ranking on Cascading Behavior Graphs for Accurate Multi-Behavior Recommendation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Geonwoo Ko, Minseo Jeon, Jinhong Jung

CascadingRank ranks target-behavior items by propagating personalized scores through separate user–item graphs arranged in a supplied behavior sequence, combining graph smoothness, user query information, and scores from preceding behaviors. In offline leave-one-out tests on Taobao, Tmall, and Tenrec, it achieved the best reported HR@10 and NDCG@10 on all three datasets, without establishing deployment or causal mechanism effects.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.