3 papers in the archive (2025–2026), average empirical rigor 7.3/10, average math complexity 5.5/10. Quadrant mix: Holy Grail ×2, Street Traders ×1.
Works mostly in Market Simulation & Agent-Based Models, Machine Learning for Market Forecasting, NLP & LLMs in Finance, Portfolio Optimization.
Frequent co-authors: Zeping Li (1), Guancheng Wan (1), Keyang Chen (1), Yiwen Zhao (1), Philip Torr (1), Guangnan Ye (1).
Scores are our LLM-assisted heuristics (methodology), not peer review or citation counts. Author pages are generated from paper metadata; name variants may split one person across pages. arXiv author page →
Ordered by a blend of empirical rigor (60%) and math complexity (40%).
Conditional Autoencoders (CAEs) offer a flexible, interpretable approach for estimating latent asset-pricing factors from firm characteristics. However, existing studies usually limit the latent factor dimension to around K=5 due to concerns that larger K can degrade performance. To overcome this ch
Generative models for financial time series often create data that look realistic and even reproduce stylized facts such as fat tails or volatility clustering. However, these apparent successes break down under trading backtests: models like GANs or WGAN-GP frequently collapse, yielding extreme and
Recent works have increasingly applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena. However, a crucial question arises: Do LLM agents’ behaviors align with real market participants? This alignment