Authors: Yongqiang Han, Hao Wang, Kefan Wang, Likang Wu, Zhi Li, Wei Guo, Yong Liu, Defu Lian, Enhong Chen

Published on: March 26, 2024

Impact Score: 7.6

Arxiv code: Arxiv:2403.17603

Summary

• What is new: The introduction of the Efficient Behavior Sequence Miner (EBM) coupled with hard and soft denoising modules and a contrastive loss function for better handling of multi-behavior data in recommendation systems.
• Why this is important: The challenge of long user behavior sequences and noise in the data, which affects the efficiency and accuracy of recommendation systems.
• What the research proposes: A new model, EBM, that captures complex user behavior patterns efficiently while reducing noise through specialized denoising modules.
• Results: Experiments on real-world datasets showed that this approach is more effective and efficient than existing methods in dealing with multi-behavior sequential recommendation.

Technical Details

Technological frameworks used: nan

Models used: Efficient Behavior Sequence Miner (EBM), hard and soft denoising modules, contrastive loss function

Data used: real-world datasets

Potential Impact

This innovation could significantly impact the e-commerce industry, content streaming services, and online advertising markets, benefiting companies focused on personalized user experiences.

Want to implement this idea in a business?

We have generated a startup concept here: ClearPathAI.