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

Abstract

Conversion prediction plays an important role in online advertising since Cost-Per-Action (CPA) has become one of the primary campaign performance objectives in the industry. Unlike click prediction, conversions have different types in nature, and each type may be associated with different decisive factors. In this paper, we formulate conversion prediction as a multi-task learning problem, so that the prediction models for different types of conversions can be learned together. These models share feature representations, but have their specific parameters, providing the benefit of information-sharing across all tasks. We then propose Multi-Task Field-weighted Factorization Machine (MT-FwFM) to solve these tasks jointly. Our experiment results show that, compared with two state-of-the-art models, MT-FwFM improve the AUC by 0.74% and 0.84% on two conversion types, and the weighted AUC across all conversion types is also improved by 0.50%.

arXiv commentSIGKDD

References in corpus (4)

• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
• Neural Factorization Machines for Sparse Predictive Analytics
• Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising
• A Nonparametric Delayed Feedback Model for Conversion Rate Prediction

Cited by in corpus (16)

• $F{M}^2$: Field-matrixed Factorization Machines for Recommender Systems
• AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
• An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions
• Bid Shading in The Brave New World of First-Price Auctions
• Ads Recommendation in a Collapsed and Entangled World
• HIEN: Hierarchical Intention Embedding Network for Click-Through Rate Prediction
• Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback
• Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction
• User Response Prediction in Online Advertising
• DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving
• Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
• Privacy Preserving Conversion Modeling in Data Clean Room
• Contrastive Learning for Conversion Rate Prediction
• Time-Aware Prospective Modeling of Users for Online Display Advertising
• Practical Multi-Task Learning for Rare Conversions in Ad Tech
• Masked Multi-Domain Network: Multi-Type and Multi-Scenario Conversion Rate Prediction with a Single Model