Researchers have developed a new model called DANet to improve conversion rate prediction in e-commerce recommendation systems. DANet specifically addresses the impact of item discount rates, a factor often overlooked in existing models. The system utilizes a time-frequency transformation module with Fourier transforms to analyze discount trends, a distribution de-bias module to correct for biases in user-specific discount data, and a supervised regression task to enhance discount rate representation. Successfully deployed on the Alibaba Tmall APP, DANet has shown significant improvements in both offline AUC and online pCVR and GMV metrics. AI
IMPACT Enhances e-commerce recommendation systems by optimizing conversion rate prediction through discount analysis.
RANK_REASON The cluster contains a research paper detailing a new model and its experimental results. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
