Researchers have developed a new industrial recommendation framework called COTTI, designed to improve performance during promotional events. COTTI separates historical representation learning from event-time score adjustments, using techniques like Cross-Period Contrastive Alignment and Active Re-weighting. An online experiment showed COTTI achieved a 3.14% increase in conversion rate and a 2.68% rise in revenue per mille compared to the existing HDR model. AI
IMPACT Improves recommendation system performance during promotional periods, potentially increasing revenue and conversion rates for e-commerce platforms.
RANK_REASON Academic paper detailing a new recommendation framework. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →