←Back to feed
🧠 AI⚪ NeutralImportance 4/10
MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms
arXiv – CS AI|Jinqi Wu, Sishuo Chen, Zhangming Chan, Yong Bai, Lei Zhang, Sheng Chen, Chenghuan Hou, Xiang-Rong Sheng, Han Zhu, Jian Xu, Bo Zheng, Chaoyou Fu||3 views
🤖AI Summary
Researchers have created MAC, the first public conversion rate prediction dataset featuring labels from multiple attribution mechanisms, along with PyMAL, an open-source library for multi-attribution learning approaches. The study introduces a new method called Mixture of Asymmetric Experts (MoAE) that significantly outperforms existing state-of-the-art multi-attribution learning methods.
Key Takeaways
- →MAC is the first public CVR dataset with multiple attribution mechanism labels, addressing a key data gap in multi-attribution learning research.
- →Multi-attribution learning consistently improves performance across different settings, especially for users with long conversion paths.
- →Performance gains scale with objective complexity, but adding auxiliary objectives can be counterproductive for first-click conversion targets.
- →The proposed MoAE method substantially surpasses existing state-of-the-art multi-attribution learning approaches.
- →Both the MAC benchmark and PyMAL algorithm library are publicly available for reproducible research.
#machine-learning#conversion-prediction#multi-attribution#benchmark#open-source#research#dataset#deep-learning
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Related Articles