Researchers have developed DASH, a novel decision-aware user simulator designed to improve the evaluation of online advertising and recommendation systems. Unlike previous simulators that focus solely on observable actions like clicks and use single-domain histories, DASH incorporates heterogeneous cross-domain data and generates both thinking traces and behavioral actions. This approach aims to provide a more comprehensive view of user preferences and enhance the diagnostic value of simulations. Experiments on real-world data from Tencent advertising demonstrated DASH's effectiveness and efficiency. AI
IMPACT Enhances the fidelity and diagnostic value of user simulators for online advertising and recommendation systems.
RANK_REASON The cluster contains a research paper detailing a new method for user simulation in online advertising. [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 →
