The Interpretability of LSTM Models for Predicting Oil Company Stocks: Impact of Correlated Features

Abstract

Oil companies are among the largest companies in the world whose economic indicators in the global stock market have a great impact on the world economy (Stevens, 2018) and market due to their relation to gold (Aijaz et al., 2016), crude oil (Henriques & Sadorsky, 2008), and the dollar (Huang et al., 1996). This study investigates the impact of correlated features on the interpretability of long short-term memory (LSTM) (Peters, 2001) models for predicting oil company stocks. To achieve this, we designed a standard long short-term memory (LSTM) network and trained it using various correlated data sets. Our approach is aimed at improving the accuracy of stock price prediction by considering the multiple factors affecting the market, such as crude oil prices, gold prices, and the US dollar. The results demonstrate that adding a feature correlated with oil stocks does not improve the interpretability of LSTM models. These findings suggest that while LSTM models may be effective in predicting stock prices, their interpretability may be limited. Caution should be exercised when relying solely on LSTM models for stock price prediction as their lack of interpretability may make it difficult to fully understand the underlying factors driving stock price movements. We have employed complexity analysis to support our argument, considering that financial markets encompass a form of physical complex system (Peters, 2001). One of the fundamental challenges faced in utilizing LSTM models for financial markets lies in interpreting the unexpected feedback dynamics within them.