Research

Working Papers

Carbon emission and asset prices: new evidence from machine learning (with Feng Li)

                We predict carbon emissions of US-listed firms with XGBoost and find reversed carbon premium after 2016.

                Presentations at CICF 2023, 2023CFRI&CIRF Joint Conference, SBSICF 2023, CMCSR 2023. (Manuscript here, slides here)

Carbon awareness and return co-movement (with Feng Li)

                Investors care about carbon risk only after 2012. (Manuscript here)

Can Convolutional Neural Networks predict the Chinese stock market? Improved method based on large order net inflow rate (《卷积神经网络能否预测中国股市？基于大单净流入率的改进方法》 in Chinese, with Yuqiao Fang and Feng Li)

                We propose a simple but effective method to improve the predictability power of CNN in the Chinese Stock market. (Manuscript here)

Work in Progress

Private Responsible Engagements and ESG Performance (with Danting Chang and Guanmin Liao )

                Institutional investors visit firms “privately”, which improves firms’ ESG performance.

Large language models as agents: ethics and preferences (with Shumiao Ouyang and Hayong yun)

        Large language models do exhibit consistent risk preferences and finetuning has unintended consequences on their risk preferences.