Reproduce “Forecasting Sales Delay through Time-aware Analysis of Sales Events in Textual Reports” 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
Masaya Tsunokake, Yuta Koreeda, Yuhei Niwa, Terufumi Morishita, Teppei Inoue, Hiroaki Ozaki, Yasuhiro Sogawa
The authors forecast signed day differences between actual and scheduled order dates in make-to-order B2B sales. They extract dated prospects, sales phases, and sentiment from reports, combining confidence and status features with project information. On one Japanese company's test data, the method achieved a mean absolute error of 70.80 days, 16% lower than the baseline; this shows predictive performance, not client intent.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.