Evaluating ARIMA and LSTM Approaches for Predicting S&P 500 Index Movements: A Comparative Analysis

Keming Zhang

2023

Abstract

Within the sphere of equity market trading, precise price prediction is paramount for steering investment strategies and increasing returns. This manuscript presents a comparative study of two renowned time series forecasting models, the AutoRegressive Integrated Moving Average (ARIMA) model and the Long Short-Term Memory (LSTM) model. Given the S&P 500’s significance as an investor benchmark, this study employs historical S&P 500 price data from 2018 to 2023 to appraise the predictive efficacy of both ARIMA and LSTM models. The findings in this instance underscore the superior precision of the ARIMA model over the LSTM model. Nevertheless, it is imperative to highlight that the selection between ARIMA and LSTM models ought to be dependent on the specific attributes of the data and the forecasting horizons in question. This investigation illuminates the respective advantages and limitations of both models, offering valuable insights for investors and scholars traversing the multifaceted terrain of financial markets. Subsequent research could extend this inquiry by investigating additional time-series models to improve the proficiency of stock price prognostications.

Paper Citation

in Harvard Style

Zhang K. (2023). Evaluating ARIMA and LSTM Approaches for Predicting S&P 500 Index Movements: A Comparative Analysis. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 444-450. DOI: 10.5220/0012808700003885

in Bibtex Style

@conference{daml23,
author={Keming Zhang},
title={Evaluating ARIMA and LSTM Approaches for Predicting S&P 500 Index Movements: A Comparative Analysis},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={444-450},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012808700003885},
isbn={978-989-758-705-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Evaluating ARIMA and LSTM Approaches for Predicting S&P 500 Index Movements: A Comparative Analysis
SN - 978-989-758-705-4
AU - Zhang K.
PY - 2023
SP - 444
EP - 450
DO - 10.5220/0012808700003885
PB - SciTePress