Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Collaborative Contrastive Network for Click-Through Rate Prediction

Chen Gao, Zixin Zhao, Sihao Hu, Lv Shao, Tong Liu

TL;DR

A more general and robust CTR prediction approach, dubbed Collaborative Contrastive Network (CCN), which learns to identify two item clusters that can represent the user's interests and disinterests, via leveraging the collaborative relationship of co-click/co-non-click or the non-collaborative relationship of mono-click as the supervision signal for contrastive learning.

Abstract

E-commerce platforms provide entrances for customers to enter mini-apps to meet their specific shopping needs. At the entrance of a mini-app, a trigger item recommended based on customers' historical preferences, is displayed to attract customers to enter the mini-app. Existing Click-Through Rate (CTR) prediction approaches have two significant weaknesses: (i) A portion of customer entries is driven by their interest in the mini-app itself rather than the trigger item. In such cases, approaches highly hinging on the trigger item tend to recommend similar items, thus misunderstanding the customers' real intention; (ii) Approaches that consider customers' intention toward mini-apps, require the regular existence of mini-apps for customers to cultivate routine shopping habits, making such approaches less robust for mini-apps that are available for only short periods (1 or 3 days) in Explosive Promotional Scenarios (EPS), such as the Black Friday and China's Double 11 Shopping Carnival. To address the above-mentioned issues, we introduce a more general and robust CTR prediction approach, dubbed Collaborative Contrastive Network (CCN). Given a user, CCN learns to identify two item clusters that can represent the user's interests and disinterests, via leveraging the collaborative relationship of co-click/co-non-click or the non-collaborative relationship of mono-click as the supervision signal for contrastive learning. This paradigm does not need to explicitly estimate user's binary entry intention and avoids amplifying the impact of the trigger item. Online A/B testing on large-scale real-world data demonstrates that CCN sets a new state-of-the-art performance on Taobao, boosting CTR by 12.3% and order volume by 12.7%.

Collaborative Contrastive Network for Click-Through Rate Prediction

TL;DR

A more general and robust CTR prediction approach, dubbed Collaborative Contrastive Network (CCN), which learns to identify two item clusters that can represent the user's interests and disinterests, via leveraging the collaborative relationship of co-click/co-non-click or the non-collaborative relationship of mono-click as the supervision signal for contrastive learning.

Abstract

E-commerce platforms provide entrances for customers to enter mini-apps to meet their specific shopping needs. At the entrance of a mini-app, a trigger item recommended based on customers' historical preferences, is displayed to attract customers to enter the mini-app. Existing Click-Through Rate (CTR) prediction approaches have two significant weaknesses: (i) A portion of customer entries is driven by their interest in the mini-app itself rather than the trigger item. In such cases, approaches highly hinging on the trigger item tend to recommend similar items, thus misunderstanding the customers' real intention; (ii) Approaches that consider customers' intention toward mini-apps, require the regular existence of mini-apps for customers to cultivate routine shopping habits, making such approaches less robust for mini-apps that are available for only short periods (1 or 3 days) in Explosive Promotional Scenarios (EPS), such as the Black Friday and China's Double 11 Shopping Carnival. To address the above-mentioned issues, we introduce a more general and robust CTR prediction approach, dubbed Collaborative Contrastive Network (CCN). Given a user, CCN learns to identify two item clusters that can represent the user's interests and disinterests, via leveraging the collaborative relationship of co-click/co-non-click or the non-collaborative relationship of mono-click as the supervision signal for contrastive learning. This paradigm does not need to explicitly estimate user's binary entry intention and avoids amplifying the impact of the trigger item. Online A/B testing on large-scale real-world data demonstrates that CCN sets a new state-of-the-art performance on Taobao, boosting CTR by 12.3% and order volume by 12.7%.

Paper Structure

This paper contains 12 sections, 11 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Proposed Method
  3. Overview
  4. CTR Prediction
  5. Collaborative Contrastive Learning
  6. Inference Deployment
  7. Experiments
  8. Dataset and Experimental Setup
  9. Offline Performance Comparison
  10. Ablation Study
  11. Online A/B Testing
  12. Conclusion

Figures (3)

  • Figure 1: Trigger-Induced Recommendation in Mini-Apps
  • Figure 2: Division of positive and negative sets for the In-Page Exposure Context items.
  • Figure 3: The architecture of Collaborative Contrastive Network (CCN), which consists of two modules: the CTR prediction module to accurately estimate a click-through probability for a target item, and the collaborative module to generate item embeddings that represent user's interest and disinterest.