Forecasting the Performance of US Stock Market Indices During COVID-19: RF vs LSTM

TL;DR

This paper compares Random Forest and LSTM models for forecasting US stock market indices during COVID-19, demonstrating how machine learning can aid traders in risk management and profit maximization.

Contribution

It introduces a comparative analysis of RF and LSTM models specifically tailored for pandemic-affected stock market forecasting, incorporating hyperparameter tuning and preprocessing techniques.

Findings

High-accuracy forecasts achieved with optimized models

LSTM outperforms Random Forest in predictive accuracy

Forecasting aids traders in risk mitigation and profit improvement

Abstract

The US stock market experienced instability following the recession (2007-2009). COVID-19 poses a significant challenge to US stock traders and investors. Traders and investors should keep up with the stock market. This is to mitigate risks and improve profits by using forecasting models that account for the effects of the pandemic. With consideration of the COVID-19 pandemic after the recession, two machine learning models, including Random Forest and LSTM are used to forecast two major US stock market indices. Data on historical prices after the big recession is used for developing machine learning models and forecasting index returns. To evaluate the model performance during training, cross-validation is used. Additionally, hyperparameter optimizing, regularization, such as dropouts and weight decays, and preprocessing improve the performances of Machine Learning techniques. Using high-accuracy machine learning techniques, traders and investors can forecast stock market behavior, stay ahead of their competition, and improve profitability. Keywords: COVID-19, LSTM, S&P500, Random Forest, Russell 2000, Forecasting, Machine Learning, Time Series JEL Code: C6, C8, G4.