Online Interaction Detection for Click-Through Rate Prediction

TL;DR

This paper introduces Online Random Intersection Chains, a novel, interpretable, and update-friendly method for detecting feature interactions in click-through rate prediction, improving model performance on streaming data.

Contribution

The paper presents a new online interaction detection technique based on frequent itemset mining, enabling real-time updates and broad applicability to CTR models.

Findings

Effective interaction detection on benchmark datasets

High interpretability of discovered interactions

Supports streaming data without retraining

Abstract

Click-Through Rate prediction aims to predict the ratio of clicks to impressions of a specific link. This is a challenging task since (1) there are usually categorical features, and the inputs will be extremely high-dimensional if one-hot encoding is applied, (2) not only the original features but also their interactions are important, (3) an effective prediction may rely on different features and interactions in different time periods. To overcome these difficulties, we propose a new interaction detection method, named Online Random Intersection Chains. The method, which is based on the idea of frequent itemset mining, detects informative interactions by observing the intersections of randomly chosen samples. The discovered interactions enjoy high interpretability as they can be comprehended as logical expressions. ORIC can be updated every time new data is collected, without being retrained on historical data. What's more, the importance of the historical and latest data can be controlled by a tuning parameter. A framework is designed to deal with the streaming interactions, so almost all existing models for CTR prediction can be applied after interaction detection. Empirical results demonstrate the efficiency and effectiveness of ORIC on three benchmark datasets.