Kuaishou Tech

May 18, 2026 · Artificial Intelligence

How ALM‑MTA Improves Multi‑Touch Attribution with Front‑Door Identification and Adversarial Modeling

The ALM‑MTA method combines front‑door causal adjustment with an adversarial proxy for the unobserved mediator, eliminating hidden confounding in multi‑touch attribution and delivering more reliable uplift estimates that boosted Kuaishou's DAU by 0.6% and AUC by 11% over SOTA baselines, as reported in an ICLR 2026 paper.