Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading Performance

A pairs trading strategy (PTS) constructs and monitors a stationary portfolio by shorting (longing) when the portfolio is adequately over- (under-)priced measured by a predetermined open threshold. We close this position to earn the price differences when the portfolio’s value reverts bac...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei-Lun Kuo, Wei-Che Chang, Tian-Shyr Dai, Ying-Ping Chen, Hao-Han Chang
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9875266/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126931320635392
author Wei-Lun Kuo
Wei-Che Chang
Tian-Shyr Dai
Ying-Ping Chen
Hao-Han Chang
author_facet Wei-Lun Kuo
Wei-Che Chang
Tian-Shyr Dai
Ying-Ping Chen
Hao-Han Chang
author_sort Wei-Lun Kuo
collection DOAJ
description A pairs trading strategy (PTS) constructs and monitors a stationary portfolio by shorting (longing) when the portfolio is adequately over- (under-)priced measured by a predetermined open threshold. We close this position to earn the price differences when the portfolio’s value reverts back to the mean level. When the portfolio is significantly over- (under-)priced measured by another predetermined stop-loss threshold, we close the position to stop loss. This paper develops a two-stage deep learning method to improve the investment performance of a PTS. Note that the literature executes a PTS by selecting the best trigger threshold (a combination of open and stop-loss thresholds) from a restricted, heuristically-determined set of trigger thresholds. Such a design significantly degrades investment performance. However, selecting the best threshold from all possible thresholds yields a non-converged training problem. To resolve this dilemma, we propose in the first stage of our method a representative label mechanism by which to construct a set of candidate trigger thresholds based on all possible thresholds and then train a deep learning (DL) model to select the best from the set. Experiments demonstrate that the proposed first-stage method avoids the non-converged training problem and outperforms most state-of-the-art methods. To further reduce the trading risk, the second stage trains another DL with the profitability of each trade labeled by executing the PTS with trigger thresholds recommended in the first-stage mechanism to remove unprofitable trades. Compared to models that indirectly judge profitability by price movement similarity without considering the quality of the recommended trigger thresholds, our model produces higher win rates and average profits. Furthermore, we find that training with the PTS portfolio value process exhibiting time invariance clearly outperforms training with only time-varying stock/return processes, even though the latter training set contains more information. This is because unpredictable changes in market trends cause the model to learn time-varying patterns from the training set that may not apply to the testing set.
format Article
id doaj-art-aee9964344844375a9db1eca67b8794d
institution OA Journals
issn 2169-3536
language English
publishDate 2022-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-aee9964344844375a9db1eca67b8794d2025-08-20T02:33:48ZengIEEEIEEE Access2169-35362022-01-0110970309704610.1109/ACCESS.2022.32040569875266Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading PerformanceWei-Lun Kuo0Wei-Che Chang1Tian-Shyr Dai2https://orcid.org/0000-0002-9226-3056Ying-Ping Chen3https://orcid.org/0000-0002-5979-6926Hao-Han Chang4https://orcid.org/0000-0003-2064-5941Institute of Data Science and Engineering, National Yang Ming Chiao Tung University (NYCU), Hsinchu, TaiwanInstitute of Computer Science and Engineering, National Yang Ming Chiao Tung University (NYCU), Hsinchu, TaiwanDepartment of Information Management and Finance, National Yang Ming Chiao Tung University (NYCU), Hsinchu, TaiwanDepartment of Computer Science, National Yang Ming Chiao Tung University (NYCU), Hsinchu, TaiwanDepartment of Information Management and Finance, National Yang Ming Chiao Tung University (NYCU), Hsinchu, TaiwanA pairs trading strategy (PTS) constructs and monitors a stationary portfolio by shorting (longing) when the portfolio is adequately over- (under-)priced measured by a predetermined open threshold. We close this position to earn the price differences when the portfolio’s value reverts back to the mean level. When the portfolio is significantly over- (under-)priced measured by another predetermined stop-loss threshold, we close the position to stop loss. This paper develops a two-stage deep learning method to improve the investment performance of a PTS. Note that the literature executes a PTS by selecting the best trigger threshold (a combination of open and stop-loss thresholds) from a restricted, heuristically-determined set of trigger thresholds. Such a design significantly degrades investment performance. However, selecting the best threshold from all possible thresholds yields a non-converged training problem. To resolve this dilemma, we propose in the first stage of our method a representative label mechanism by which to construct a set of candidate trigger thresholds based on all possible thresholds and then train a deep learning (DL) model to select the best from the set. Experiments demonstrate that the proposed first-stage method avoids the non-converged training problem and outperforms most state-of-the-art methods. To further reduce the trading risk, the second stage trains another DL with the profitability of each trade labeled by executing the PTS with trigger thresholds recommended in the first-stage mechanism to remove unprofitable trades. Compared to models that indirectly judge profitability by price movement similarity without considering the quality of the recommended trigger thresholds, our model produces higher win rates and average profits. Furthermore, we find that training with the PTS portfolio value process exhibiting time invariance clearly outperforms training with only time-varying stock/return processes, even though the latter training set contains more information. This is because unpredictable changes in market trends cause the model to learn time-varying patterns from the training set that may not apply to the testing set.https://ieeexplore.ieee.org/document/9875266/Pairs trading strategyrepresentative labelingtime (in)variant datatwo-stage deep learning
spellingShingle Wei-Lun Kuo
Wei-Che Chang
Tian-Shyr Dai
Ying-Ping Chen
Hao-Han Chang
Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading Performance
IEEE Access
Pairs trading strategy
representative labeling
time (in)variant data
two-stage deep learning
title Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading Performance
title_full Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading Performance
title_fullStr Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading Performance
title_full_unstemmed Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading Performance
title_short Improving Pairs Trading Strategies Using Two-Stage Deep Learning Methods and Analyses of Time (In)variant Inputs for Trading Performance
title_sort improving pairs trading strategies using two stage deep learning methods and analyses of time in variant inputs for trading performance
topic Pairs trading strategy
representative labeling
time (in)variant data
two-stage deep learning
url https://ieeexplore.ieee.org/document/9875266/
work_keys_str_mv AT weilunkuo improvingpairstradingstrategiesusingtwostagedeeplearningmethodsandanalysesoftimeinvariantinputsfortradingperformance
AT weichechang improvingpairstradingstrategiesusingtwostagedeeplearningmethodsandanalysesoftimeinvariantinputsfortradingperformance
AT tianshyrdai improvingpairstradingstrategiesusingtwostagedeeplearningmethodsandanalysesoftimeinvariantinputsfortradingperformance
AT yingpingchen improvingpairstradingstrategiesusingtwostagedeeplearningmethodsandanalysesoftimeinvariantinputsfortradingperformance
AT haohanchang improvingpairstradingstrategiesusingtwostagedeeplearningmethodsandanalysesoftimeinvariantinputsfortradingperformance