Reproduce “Which Matters Most in Making Fund Investment Decisions? A Multi-granularity Graph Disentangled Learning Framework” 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

Chunjing Gan, Binbin Hu, Bo Huang, Tianyu Zhao, Yingru Lin, Wenliang Zhong, Zhiqiang Zhang, Jun Zhou and 1 more

MGDL recommends funds by building a graph of products and learning representations for personal interest, conformity, and risk preference. Popularity and fund type provide proxy training signals; risk preference is auxiliary and excluded from the final score. In January’s offline test, it reaches NDCG@10 0.1686 versus SASRec’s 0.1428, while gains concern clicks and purchases, not investment outcomes.

Summary by alphaXiv.

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