Speaker: 冯冠豪，香港城市大学

Inviter: 娄有成

Title: Deep Tangency Portfolio

Language: Chinese 

Time & Venue: 2024.11.12  09：30-11：00  思源楼315

Abstract: We propose a parametric approach that directly estimates the tangency portfolio weights on thousands of individual assets by integrating fundamental finance theory with deep learning models. Our deep tangency portfolio combines the market factor with a deep long-short factor constructed using a large number of firm characteristics. Applying this method to the corporate bond market, we find that the deep factor acts as a market hedge and achieves an out-of-sample annualized Sharpe ratio of 1.79. The deep tangency portfolio outperforms those constructed from commonly used observable or latent factors, with an out-of-sample annualized Sharpe ratio of 2.29. We also find evidence supporting the integration between the bond and equity markets.