FFM | BestHub

DataFunTalk

Mar 19, 2019 · Artificial Intelligence

Using Field-aware FM (FFM) Models for Unified Recall in Recommendation Systems

This article explores how Field-aware Factorization Machines (FFM) can be employed to replace multi‑path recall strategies in industrial recommendation systems, detailing model principles, embedding construction, integration of user, item and context features, performance considerations, and potential for unifying recall and ranking stages.

FFMembeddingmachine learning

0 likes · 51 min read

Using Field-aware FM (FFM) Models for Unified Recall in Recommendation Systems

Tencent Advertising Technology

Jun 4, 2018 · Artificial Intelligence

Tencent Advertising Algorithm Competition: FFM Approach and Feature Engineering by the Wenqiang Ge Team

The Wenqiang Ge team, winners of the first week of the Tencent Advertising Algorithm Competition rematch, detail their FFM-based solution, including baseline adoption, feature engineering with discretized continuous values, cross‑feature handling, and tool choices such as Feather storage and the xlearn library for fast training.

Ensemble ModelingFFMFeather

0 likes · 4 min read

Tencent Advertising Algorithm Competition: FFM Approach and Feature Engineering by the Wenqiang Ge Team

Tencent Advertising Technology

May 7, 2018 · Artificial Intelligence

Choosing Mainstream CTR Models: LightGBM, FFM, and Deep Learning Approaches

The author, a graduate student and weekly champion of the Tencent advertising algorithm contest, shares practical guidance on selecting mainstream CTR models—including LightGBM, field‑aware factorization machines, and deep learning approaches—while offering tips on feature handling, hyper‑parameter settings, and resource‑efficient implementation.

FFMLightGBMctr

0 likes · 5 min read

Choosing Mainstream CTR Models: LightGBM, FFM, and Deep Learning Approaches