Stock Price Forecasting in Presence of Covid-19 Pandemic and Evaluating Performances of Machine Learning Models for Time-Series Forecasting

TL;DR

This study compares the forecasting performance of traditional and machine learning models on stock prices during the COVID-19 pandemic, finding that autoregressive models outperform machine learning models in volatile market conditions.

Contribution

It evaluates and compares the effectiveness of LSTM, XGBoost, Autoregression, and Last Value models during a highly volatile period caused by COVID-19.

Findings

Autoregression and Last Value models achieved higher accuracy during COVID-19.

Machine learning models underperformed compared to traditional models in volatile conditions.

Strong correlation between consecutive days' prices influenced model performance.

Abstract

With the heightened volatility in stock prices during the Covid-19 pandemic, the need for price forecasting has become more critical. We investigated the forecast performance of four models including Long-Short Term Memory, XGBoost, Autoregression, and Last Value on stock prices of Facebook, Amazon, Tesla, Google, and Apple in COVID-19 pandemic time to understand the accuracy and predictability of the models in this highly volatile time region. To train the models, the data of all stocks are split into train and test datasets. The test dataset starts from January 2020 to April 2021 which covers the COVID-19 pandemic period. The results show that the Autoregression and Last value models have higher accuracy in predicting the stock prices because of the strong correlation between the previous day and the next day's price value. Additionally, the results suggest that the machine learning models (Long-Short Term Memory and XGBoost) are not performing as well as Autoregression models when the market experiences high volatility.