Deep Tangency Portfolios

47 Pages Posted: 11 Mar 2022 Last revised: 21 Nov 2022

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: November 1, 2022

Abstract

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

Feng, Guanhao and Jiang, Liang and Li, Junye and Song, Yizhi, Deep Tangency Portfolios (November 1, 2022). 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
Kowloon Tong
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
214
Abstract Views
750
rank
207,083
PlumX Metrics