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

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.

Cultural Differences in an Artificial Representation of the Human Emotional Brain System: A Deep Learning Study

“…Across the entire data set, the predictor variables are, on average, correlated at .055, and only .179% of variable combinations show a correlation greater than .8. Regardless, the redundant architecture of neural networks enables them to learn a potential similarity of input variables and make predictions even in situations of multicollinearity (e.g., Chan et al 2022; De Veaux and Ungar 1994; Paliwal and Kumar 2011).…”

Comparison of Machine Learning Techniques for Condition Assessment of Sewer Network

“…Detailed information on the filter methods can be referred to in [75]. • Wrapper methods select a subset of features by removing and adding the subsets accordingly based on the role of variables [76]. These methods usually have higher performance than filter-based methods, these approaches however are more time-consuming [77].…”

“…• Embedded methods apply the model tuning process to perform feature selection [76]. These methods are the combination of the best qualities of filter and wrapper methods in which the variable selection process and classification have been implemented simultaneously using a learning algorithm [77].…”

Natural Language Processing in Forecasting Financial Markets

“…Подієво-орієнтований підхід дозволяє за допомогою метода графів створювати модель зв'язків всередині речень та абзаців для кращої інтерпретації [6]. Це важливо, та як нехтування дрібнозернистою інформацією є критичним і може призвести до введення в оману.…”