Deep Residual Learning for Portfolio Optimization: With Attention and Switching Modules

Lecture / Panel
Open to the Public

Event poster

Dear All,

You are cordially invited to attend the upcoming FRE Lecture on Thursday, March 7th at 6PM in LC 400 (4th Floor) - Dibner Building. Dr. Jifei Wang will present a talk on the following topic:


Deep Residual Learning for Portfolio Optimization: With Attention and Switching Modules


This paper studies deep learning (DL) methodologies for portfolio optimization in the US equities market. The proposed DL paradigm exhibits substantial depth at tens of hidden layers. We demonstrate that over-fitting can be controlled with deep residual learning, and further incorporate the attention mechanisms to complete the attention-enhanced residual network (Attention ResNet) with powerful predictive properties. Over the period 2008 - H12017, the Attention ResNet strategy verified superior out-of-sample performance with an average annual Sharpe ratio of 1.77, compared with average annual Sharpe ratio of 0.81 for the ANN-based strategy and 0.69 for the linear model. The Attention ResNet is robust to over-fitting and able to optimize the degree of non-linearity in the model.

We also present a novel residual switching network that can automatically sense changes in market regimes and switch between momentum and reversal features accordingly. The residual switching network architecture combines two separate ResNets, namely a switching module that learns market condition features, and another ResNet that learns momentum and reversal feature representations.


Jeffrey Wang recently completed his PhD in Applied Mathematics at NYU Courant Institute of Mathematical Sciences in 2018, where his research interests are focused on deep learning for portfolio optimization, as well as 3D visual computing where he published in top deep learning conferences. Prior to NYU he earned his Master's degree from Georgetown University and his Bachelor’s degree from the University of Sydney. Dr. Wang is currently an Adjunct Professor at NYU, and will soon join a leading asset management firm in New York. Prior to pursuing his PhD degree, Jeffrey worked at the Bank of China and HSBC Global Banking and Markets. Dr. Wang is scheduled to teach the second half of the "Machine Learning in Financial Engineering" FRE course starting in early April. 

We look forward to having you join us next Thursday for the talk and refreshments. See attached poster for more details. Please mark your calendars.

Also, if you are interested in attending the free Quantitative Finance Weekly Seminars, please see the link below: