Reproduce “D$^3$-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market” 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
Taijie Chen, Rui Su, Siyuan Feng, Laoming Zhang, Hongyang Zhang, Haijiao Wang, Zhaofeng Ma, Jintao Ke and 1 more
D3-Subsidy plans city-level ride-hailing subsidies over time, conditioning future trajectories on realized history and a daily budget. It maps the control to capped offers under a locally linear completion-probability approximation. In a seven-day test in one city, the authors report relative lifts of 1.59% in Rides, 2.06% in GMV, and 2.31% in DRV, with no cap violations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.