TY - JOUR
T1 - Neural network with fixed noise for index-tracking portfolio optimization
AU - Kwak, Yuyeong
AU - Song, Junho
AU - Lee, Hongchul
N1 - Funding Information:
This research was supported by Brain Korea 21 FOUR, MODULABS and ZeroOne AI.
Publisher Copyright:
© 2021 Elsevier Ltd
PY - 2021/11/30
Y1 - 2021/11/30
N2 - Index tracking portfolio optimization is popular form of passive investment strategy, with a steady and profitable performance compared to an active investment strategy. Due to the revival of deep learning in recent years, several studies have been conducted to apply deep learning in the field of finance. However, most studies use deep learning exclusively to predict stock price movement, not to optimize the portfolio directly. We propose a deep learning framework to optimize the index-tracking portfolio and overcome this limitation. We use the output distribution of the softmax layer from the fixed noise as the portfolio weights and verify the tracking performance of the proposed method on the S&P 500 index. Furthermore, by performing the ablation studies on the training-validation dataset split ratio and data normalization, we demonstrate that these are critical parameters for applying deep learning to the portfolio optimization problem. We also verify the generalization performance of the proposed method through additional experiments with another index of a major stock market, the Hang Seng Index (HSI).
AB - Index tracking portfolio optimization is popular form of passive investment strategy, with a steady and profitable performance compared to an active investment strategy. Due to the revival of deep learning in recent years, several studies have been conducted to apply deep learning in the field of finance. However, most studies use deep learning exclusively to predict stock price movement, not to optimize the portfolio directly. We propose a deep learning framework to optimize the index-tracking portfolio and overcome this limitation. We use the output distribution of the softmax layer from the fixed noise as the portfolio weights and verify the tracking performance of the proposed method on the S&P 500 index. Furthermore, by performing the ablation studies on the training-validation dataset split ratio and data normalization, we demonstrate that these are critical parameters for applying deep learning to the portfolio optimization problem. We also verify the generalization performance of the proposed method through additional experiments with another index of a major stock market, the Hang Seng Index (HSI).
KW - Deep learning
KW - Fixed noise
KW - Index-tracking portfolio optimization
UR - http://www.scopus.com/inward/record.url?scp=85107867858&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2021.115298
DO - 10.1016/j.eswa.2021.115298
M3 - Article
AN - SCOPUS:85107867858
SN - 0957-4174
VL - 183
JO - Expert Systems with Applications
JF - Expert Systems with Applications
M1 - 115298
ER -