Field-aware Factorization Machines in a Real-world Online Advertising System
This work addresses the need for accurate prediction methods in computational advertising, though it is incremental as it applies an existing method to a real-world system.
The paper tackled the problem of predicting user response in online advertising by implementing Field-aware Factorization Machines (FFM) in a production system, showing it effectively predicts click-through and conversion rates beyond just winning Kaggle challenges.
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.