Deep Tangency Portfolios

Research output: Working PapersPreprint

View graph of relations


Related Research Unit(s)


Original languageEnglish
PublisherSocial Science Research Network (SSRN)
Publication statusOnline published - 11 Mar 2022


We propose a parametric approach for directly estimating the tangency portfolio weights by combining fundamental finance theory and deep learning techniques. The deep tangency portfolio is a combination of the market factor 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-hedged portfolio, the deep factor achieves a sizable risk premium 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 2.90.

Research Area(s)

  • Corporate Bond Returns, Deep Learning, Factor Models, Stochastic Discount Factor, Tangency Portfolios

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

Deep Tangency Portfolios. / Feng, Guanhao; Jiang, Liang; Li, Junye et al.

Social Science Research Network (SSRN), 2022.

Research output: Working PapersPreprint