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

  title={Field-aware Factorization Machines in a Real-world Online Advertising System},
  author={Yu-Chin Juan and Damien Lefortier and Olivier Chapelle},
  journal={Proceedings of the 26th International Conference on World Wide Web Companion},
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… 

Figures and Tables from this paper

Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising

Field-weighted Factorization Machines (FwFMs) are proposed to model the different feature interactions between different fields in a much more memory-efficient way and can achieve competitive prediction performance with only as few as 4% parameters of FFMs.

Robust Factorization Machines for User Response Prediction

This work characterize the data uncertainty using Robust Optimization (RO) paradigm to design approaches that are immune against perturbations and proposes two novel algorithms: robust factorization machine (RFM) and its field-aware variant (RFFM), under interval uncertainty.

Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising

This paper forms conversion prediction as a multi-task learning problem, so that the prediction models for different types of conversions can be learned together, and proposes Multi-Task Field-weighted Factorization Machine (MT-FwFM) to solve these tasks jointly.

An Embedded Model XG-FwFMs for Click-Through Rate

A embedded model named XG-FwFMs which use less parameters calculating and prevent the model from over-fitting is proposed which has better prediction accuracy, parameter sensitivity and effectiveness than traditional nonlinear models.

One-class Field-aware Factorization Machines for Recommender Systems with Implicit Feedbacks

A novel One-class Field-aware Factorization Machines (OCFFM) model is proposed, an efficient optimization algorithm is developed such that OCFFM can be trained on the large-scale data sets and shows its superiority over other one-class models.

FM2: Field-matrixed Factorization Machines for Recommender Systems

A novel approach to model the field information effectively and efficiently is proposed, a direct improvement of FwFM, and is named Field-matrixed Factorization Machines (FmFM, or FM2).

SEDCN: An improved Deep & Cross Network Recommendation Algorithm based on SENET

  • Jiao LiNanchang Cheng
  • Computer Science
    2022 IEEE/ACIS 22nd International Conference on Computer and Information Science (ICIS)
  • 2022
A new feature importance network model SEDCN is proposed based on deep crossover network that can learn the importance of features dynamically through the SENET mechanism and is compared with other depth models, such as DeepFM and DCN.

Co-learning Multiple Browsing Tendencies of a User by Matrix Factorization-based Multitask Learning

It is observed that instead of building independent models to predict each individual type of web page, it is more effective to use a unified model to predict a user’s future clicks on different types of web pages simultaneously.

Multi-Head Online Learning for Delayed Feedback Modeling

Multi-head modeling for delayed feedback modeling is presented, which directly quantizes conversions into multiple windows, such as day 1, day 2, day 3-7, and day 8-30, and is shown to greatly exceed the performance of known methods in online learning experiments for both conversion rate (CVR) and value per click (VPC) predictions.

Recommendation systems for online advertising

A novel Neural-Network model is derived that jointly learns a new representation of users and items in an embedded space as well as the preference relation of users over the pairs of items and given theoretical analysis.



Field-aware Factorization Machines for CTR Prediction

This paper establishes FFMs as an effective method for classifying large sparse data including those from CTR prediction, and proposes efficient implementations for training FFMs and comprehensively analyze FFMs.

Predicting response in mobile advertising with hierarchical importance-aware factorization machine

A Hierarchical Importance-aware Factorization Machine (HIFM) is developed, which provides an effective generic latent factor framework that incorporates importance weights and hierarchical learning and outperforms the contemporary temporal latent factor models.

Ad click prediction: a view from the trenches

The goal of this paper is to highlight the close relationship between theoretical advances and practical engineering in this industrial setting, and to show the depth of challenges that appear when applying traditional machine learning methods in a complex dynamic system.

Practical Lessons from Predicting Clicks on Ads at Facebook

This paper introduces a model which combines decision trees with logistic regression, outperforming either of these methods on its own by over 3%, an improvement with significant impact to the overall system performance.

Factorization Machines with libFM

Factorization approaches provide high accuracy in several important prediction problems, for example, recommender systems. However, applying factorization approaches to a new prediction problem is a

Modeling delayed feedback in display advertising

This work introduces an additional model that captures the conversion delay and helps determining whether a user that has not converted should be treated as a negative sample -- when the elapsed time is larger than the predicted delay -- or should be discarded from the training set -- when it is too early to tell.

Deep Learning over Multi-field Categorical Data - - A Case Study on User Response Prediction

This paper proposes two novel models using deep neural networks (DNNs) to automatically learn effective patterns from categorical feature interactions and make predictions of users' ad clicks and demonstrates that their methods work better than major state-of-the-art models.

Simple and Scalable Response Prediction for Display Advertising

A machine learning framework based on logistic regression that is specifically designed to tackle the specifics of display advertising and provides models with state-of-the-art accuracy.

Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions

This paper formally analyze the relationship between optimizing the Utility metric and the log loss, which is considered as one of the state-of-the-art approaches in conversion modeling and presents and analyzes a new cost weighting scheme that can be achieved in offline and online performance.

DiFacto: Distributed Factorization Machines

DiFacto is described, which uses a refined Factorization Machine model with sparse memory adaptive constraints and frequency adaptive regularization, and it is shown how to distribute DiFacto over multiple machines using the Parameter Server framework by computing distributed subgradients on minibatches asynchronously.