Reproduce “TAPES: Task-Aligned Joint Predictive Pretraining for Transaction Event Sequences” 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

Ruobing Zuo, Weiyu Han, Huilin He, Haoyu Jiang, Ze Zhao, Jie Sheng, Xiao Tan, Shuai Chen and 1 more

TAPES selects transaction properties to predict from a customer’s history according to their usefulness for a downstream task, then trains an encoder to predict the selected properties jointly. Across five public benchmarks, it has the best primary score on four and an average rank of 1.20; these are development-set results, not independent final-test evidence.

Summary by alphaXiv.

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