金融与财务学系列讲座之315期

金融与财务学系列讲座之314期

时   间：2024年12月10日14:00-15:30

地   点：李达三楼105室

主   题：Building RL-Based Generative Models for Finance

主讲人：LIN WILLIAM CONG  Cornell University

摘   要：I describe recent developments in AI and their core theme---data-driven, goal-oriented search in enlarged modeling spaces--- can be effectively applied to answer important questions in finance, provided we incorporate relevant domain knowledge. As an example, we can directly optimize arbitrary objectives of portfolio management via Transformer-based multi-sequence reinforcement learning---an alternative framework to conventional supervised-learning-based-two-step paradigms--- to allow investment interactions with the market states and training without labels. The resulting AlphaPortfolio model, as the first ``large'' generative AI models in finance, yields superior out-of-sample performances that are robust under various market conditions and economic restrictions. We further combine this reinforcement-learning framework with robust control to develop a new approach to corporate finance, treating managerial decision-making as a high-dimensional stochastic control problem with unknown market environment, non-linear impact, and dynamic feedback.  Our AlphaManager framework entails a high-fidelity "world model" of the corporate environment through supervised deep learning trained on standard financial data. The module incorporates known stylized facts and results from reduced-form models and structural estimations, and generates more effective predictions and explanations of firm outcomes. We then apply model-based deep reinforcement learning to derive the optimal managerial policy for any given objective, demonstrating significant room for improvement in modern enterprise decisions. Our ambiguity-guided approach also allows us to distinguish scenarios where theory and causal identifications are crucial from situations where predictive models trained on historical observations suffice, and to think about learning managerial objectives in generative-adversarial networks. Time-permitting, I briefly describe on-going work of using generative AI to characterize counterfactual general equilibria in the context of online credit market.

简   介: Lin William Cong is the Rudd Family Endowed Chair Professor of Management and Professor of Finance at the Johnson Graduate School of Management at Cornell University, where he is the founding faculty director for the FinTech Initiative and the founder of the Digital Economy and Financial Technology Lab (DEFT Lab). He is also an Editor at the Management Science, an associate or advisory editor for multiple leading academic and practitioner journals. Professor Cong’s research spans financial economics, information economics, AI for Finance, applied theory, FinTech, the digital economy, and entrepreneurship and innovation, and has been published in top academic journals and featured in BBC, Bloomberg, CNN, the Economist, Washington Post, etc.

金融与财务学系列讲座之315期

时   间：2024年12月11日14:00-15:30

地   点：史带楼603室

主   题：Do Investors Care about AI Externalities

主讲人: Rex Wang Renjie  Vrije Universiteit (VU) Amsterdam and Tinbergen Institute

摘   要：We answer this question by examining stock market reactions to the launch of ChatGPT—a systematic shift in the awareness of AI’s potential. Stocks with high ESG ratings outperformed those with low ESG ratings by 4pp during the two weeks following ChatGPT’s release, with a stronger effect for firms that ex-ante invested more in AI. The outperformance appears driven by investors pricing in AI-related risks, like data privacy concerns. Overall, our findings highlight the role that ESG considerations play in both shaping financial markets’ expectations of AI’s productivity potential and identifying which firms are better positioned to benefit from AI adoption.

简   介：Rex Wang Renjie is the Associate Professor of Finance at Vrije Universiteit (VU) Amsterdam & Tinbergen Institute (TI). His research interests include behavioral finance, corporate finance and governance, labor and finance, etc. His work has been published in Journal of Financial and Quantitative Analysis, Review of Finance, and Financial Management.

金融与财务学系

2024-12-6