FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems
Paper recorded by Signals 4 on 2026-10-09 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-09 on arXiv · recorded by Signals 4 on 2026-10-12
Category: cs.AI · 人工智能 · first seen 2026-10-12
Abstract
Production recommender systems have feature-lifecycle asymmetry: adding new features must produce gains on some metric, while feature removal must not regress any metric. In practice, feature deprecation is hard to prioritize as a feature can fail to be removed if it interacts with other features, its importance changes daily, it cannot be evaluated before production models change or data drift oc
Read on arXiv →
Cite this page: FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems: the #351 most recent of 960 cs.AI papers we have recorded (as of 2026-10-09). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/forte-a-production-framework-for-feature-evaluation-and-deprecation-in-industria.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free