A Correlation-Embedded Attention Module to Mitigate Multicollinearity: An Algorithmic Trading Application

Jireh Yi-Le Chan, Steven Mun Hong Leow, Khean Thye Bea, Wai Khuen Cheng, Seuk Wai Phoong, Zeng-Wei Hong, Jim-Min Lin and Yen-Lin Chen
Additional contact information
Jireh Yi-Le Chan: Faculty of Business and Finance, University Tunku Abdul Rahman, Perak 31900, Malaysia
Steven Mun Hong Leow: Faculty of Business and Finance, University Tunku Abdul Rahman, Perak 31900, Malaysia
Khean Thye Bea: Faculty of Business and Finance, University Tunku Abdul Rahman, Perak 31900, Malaysia
Wai Khuen Cheng: Faculty of Information and Communication Technology, University Tunku Abdul Rahman, Perak 31900, Malaysia
Seuk Wai Phoong: Department of Operation and Management Information System, Faculty of Business and Accountancy, University of Malaya, Kuala Lumpur 50603, Malaysia
Zeng-Wei Hong: Department of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, Taiwan
Jim-Min Lin: Department of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, Taiwan
Yen-Lin Chen: Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 106344, Taiwan

Mathematics, 2022, vol. 10, issue 8, 1-13

Abstract: Algorithmic trading is a common topic researched in the neural network due to the abundance of data available. It is a phenomenon where an approximately linear relationship exists between two or more independent variables. It is especially prevalent in financial data due to the interrelated nature of the data. The existing feature selection methods are not efficient enough in solving such a problem due to the potential loss of essential and relevant information. These methods are also not able to consider the interaction between features. Therefore, we proposed two improvements to apply to the Long Short-Term Memory neural network (LSTM) in this study. It is the Multicollinearity Reduction Module (MRM) based on correlation-embedded attention to mitigate multicollinearity without removing features. The motivation of the improvements is to allow the model to predict using the relevance and redundancy within the data. The first contribution of the paper is allowing a neural network to mitigate the effects of multicollinearity without removing any variables. The second contribution is improving trading returns when our proposed mechanisms are applied to an LSTM. This study compared the classification performance between LSTM models with and without the correlation-embedded attention module. The experimental result reveals that a neural network that can learn the relevance and redundancy of the financial data to improve the desired classification performance. Furthermore, the trading returns of our proposed module are 46.82% higher without sacrificing training time. Moreover, the MRM is designed to be a standalone module and is interoperable with existing models.

Keywords: algorithmic trading; multicollinearity; feature selection; neural network; classification (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/8/1231/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/8/1231/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:8:p:1231-:d:789775

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().