Meituan Technology Team
Mar 10, 2022 · Artificial Intelligence
Heterogeneous Ad Mixing and Candidate Expansion for Location-Based Services in Meituan In‑Store Advertising
To overcome the limited store‑candidate pool in Meituan’s location‑based in‑store advertising, the authors propose a heterogeneous mixing system that expands candidates with product ads, uses a shared‑representation network and Transformer‑based combination estimator, and applies a Thompson‑sampling cold‑start strategy, boosting RPM by up to 15 % while keeping latency low.
AdvertisingLocation-Based Servicescandidate expansion
0 likes · 19 min read
