Deep Tangency Portfolios
47 Pages Posted: 11 Mar 2022 Last revised: 21 Nov 2022
Date Written: November 1, 2022
We propose a parametric approach for directly estimating the optimal portfolio weights based on a fundamental economic theory by employing deep learning techniques. The deep tangency portfolio is a combination of the market portfolio and a deep long-short factor constructed using a large number of characteristics. We apply our approach to the corporate bond market. Albeit acting as a market-hedge portfolio, the deep factor achieves a sizable market price of risk with an out-of-sample annualized Sharpe ratio of 2.08. The deep tangency portfolio outperforms those constructed from commonly used observable or latent factors with an out-of-sample annualized Sharpe ratio of 3.34. In addition, our findings provide further empirical evidence supporting the integration between bond and equity markets.
Keywords: Stochastic Discount Factor, Tangency Portfolios, Factor Models, Deep Learning, Corporate Bond Returns.
JEL Classification: C1, G1
Suggested Citation: Suggested Citation