Deep Tangency Portfolios

55 Pages Posted: 11 Mar 2022 Last revised: 30 Sep 2023

See all articles by Guanhao Feng

Guanhao Feng

City University of Hong Kong (CityU)

Liang Jiang

Fudan University - Fanhai International School of Finance (FISF)

Junye Li

Fudan University - School of Management

Yizhi Song

City University of Hong Kong (CityU)

Date Written: September 27, 2023

Abstract

We propose a parametric approach to directly estimate the tangency portfolio weights on high-dimensional individual assets by combining fundamental finance theory with deep learning techniques. The deep tangency portfolio combines the market factor and a deep long-short factor constructed using a large number of firm characteristics. We apply our approach to the corporate bond market. The deep factor acts as a market hedge and achieves a sizable market price of risk with 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.

Keywords: Tangency Portfolios, Deep Learning, Factor Models, Portfolio Optimization, Corporate Bonds.

JEL Classification: C45,G11,G12.

Suggested Citation

Feng, Guanhao and Jiang, Liang and Li, Junye and Song, Yizhi, Deep Tangency Portfolios (September 27, 2023). Available at SSRN: https://ssrn.com/abstract=3971274 or http://dx.doi.org/10.2139/ssrn.3971274

Guanhao Feng (Contact Author)

City University of Hong Kong (CityU) ( email )

83 Tat Chee Avenue
Hong Kong

Liang Jiang

Fudan University - Fanhai International School of Finance (FISF) ( email )

220 Handan Road
Shanghai, 200433
China

Junye Li

Fudan University - School of Management ( email )

No. 670, Guoshun Road
No.670 Guoshun Road
Shanghai, 200433
China

Yizhi Song

City University of Hong Kong (CityU) ( email )

83 Tat Chee Avenue
Kowloon
Hong Kong

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
662
Abstract Views
2,118
Rank
75,689
PlumX Metrics