Financial Thought Experiment: A GAN-based Approach to Vast Robust Portfolio Selection

In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI '20), 2020

7 Pages Posted: 23 Jun 2020

See all articles by Chi Seng Pun

Chi Seng Pun

Nanyang Technological University (NTU) - School of Physical and Mathematical Sciences

Lei Wang

Nanyang Technological University (NTU) - School of Physical and Mathematical Sciences

Hoi Ying Wong

The Chinese University of Hong Kong (CUHK) - Department of Statistics

Date Written: May 17, 2020

Abstract

Modern day trading practice resembles a thought experiment, where investors imagine various possibilities of future stock market and invest accordingly. Generative adversarial network (GAN) is highly relevant to this trading practice in two ways. First, GAN generates synthetic data by a neural network that is technically indistinguishable from the reality, which guarantees the reasonableness of the experiment. Second, GAN generates multitudes of fake data, which implements half of the experiment. In this paper, we present a new architecture of GAN and adapt it to portfolio risk minimization problem by adding a regression network to GAN (implementing the second half of the experiment). The new architecture is termed GANr. Battling against two distinctive networks: discriminator and regressor, GANr’s generator aims to simulate a stock market that is close to the reality while allow for all possible scenarios. The resulting portfolio resembles a robust portfolio with data-driven ambiguity. Our empirical studies show that GANr portfolio is more resilient to bleak financial scenarios than CLSGAN and LASSO portfolios.

Keywords: Financial Thought Experiment, GAN, Portfolio Selection

Suggested Citation

Pun, Chi Seng and Wang, Lei and Wong, Hoi Ying, Financial Thought Experiment: A GAN-based Approach to Vast Robust Portfolio Selection (May 17, 2020). In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI '20), 2020, Available at SSRN: https://ssrn.com/abstract=3613739 or http://dx.doi.org/10.2139/ssrn.3613739

Chi Seng Pun (Contact Author)

Nanyang Technological University (NTU) - School of Physical and Mathematical Sciences ( email )

SPMS-MAS-05-22
21 Nanyang Link
Singapore, 637371
Singapore
(+65) 6513 7468 (Phone)

HOME PAGE: http://personal.ntu.edu.sg/cspun/

Lei Wang

Nanyang Technological University (NTU) - School of Physical and Mathematical Sciences ( email )

S3 B2-A28 Nanyang Avenue
Singapore, 639798
Singapore

Hoi Ying Wong

The Chinese University of Hong Kong (CUHK) - Department of Statistics ( email )

Shatin, N.T.
Hong Kong

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

Paper statistics

Downloads
135
Abstract Views
529
rank
257,832
PlumX Metrics