New benchmark and library advance multi-attribution learning for conversion rate prediction

Researchers have introduced the Multi-Attribution Benchmark (MAC), the first public dataset for conversion rate prediction that includes labels from multiple attribution mechanisms. This benchmark aims to advance multi-attribution learning (MAL), a paradigm that improves model performance by leveraging diverse conversion labels. The study also presents PyMAL, an open-source library for MAL methods, and introduces Mixture of Asymmetric Experts (MoAE), a novel approach that demonstrates superior performance on the MAC dataset. AI

IMPACT This research provides a new benchmark and tools to advance multi-attribution learning, potentially improving the accuracy of conversion rate prediction models.

RANK_REASON The cluster describes a new academic paper introducing a benchmark dataset and a novel model for a specific machine learning task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Jinqi Wu
• MAC
• Mixture of Asymmetric Experts
• Multi-Attribution Benchmark

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →