Field-aware Factorization Machines in a Real-world Online Advertising System

Code

• github.com/cpapadimitriou/Click-Through-Rate-prediction
  none★ 11
• github.com/guestwalk/libffm
  none★ 0
• github.com/ycjuan/libffm
  none★ 0

Abstract

Predicting user response is one of the core machine learning tasks in computational advertising. Field-aware Factorization Machines (FFM) have recently been established as a state-of-the-art method for that problem and in particular won two Kaggle challenges. This paper presents some results from implementing this method in a production system that predicts click-through and conversion rates for display advertising and shows that this method it is not only effective to win challenges but is also valuable in a real-world prediction system. We also discuss some specific challenges and solutions to reduce the training time, namely the use of an innovative seeding algorithm and a distributed learning mechanism.

Reproductions