Forecasting Performance Comparison: LSTM Model vs. Dynamic and Static Forecasting of ARIMA and Random Walk Models - Evidence from S&P500
- 5 January 2026
- journal article
- Published by Gazi University Journal of Science in Gazi University Journal of Science
- No. Advanced O
Abstract
This paper re-evaluates the forecasting performance of Long Short-Term Memory (LSTM) models against traditional Autoregressive Integrated Moving Average (ARIMA) and Random Walk (RW) models using S&P 500 index data. The LSTM models in the literature, which utilize observed lagged values for their forecasting (static forecasting), are compared to traditional models that use recursive, self-generated predictions for forecasting (dynamic forecasting). To provide comparable statistics, we gather relevant statistics for the static forecasting of ARIMA and RW models. We repeat the exercise for three different cross-validation schemes. The empirical evidence presented here suggests that the static forecasting power of static ARIMA and RW models consistently matches or outperforms that of LSTMs. Moreover, we find that while traditional models remain robust across varying sample sizes, the performance of LSTMs decreases when the training datasets are reduced. The empirical evidence presented here suggests that the reported superiority of LSTM in financial time series forecasting might be due to the forecasting method that is employed rather than a genuine predictive advantage.Keywords
This publication has 51 references indexed in Scilit:
- Deep Learning and Machine Learning Insights Into the Global Economic Drivers of the Bitcoin PriceJournal of Forecasting, 2025
- Image analysis and LSTM methods for forecasting surficial displacements of a landslide triggered by snowfall and rainfallLandslides, 2024
- Automatic Indian sign language recognition using MediaPipe holistic and LSTM networkMultimedia Tools and Applications, 2023
- Multi-step Time Series Forecasting of Electric Load Using Machine Learning Models2018
- Evaluating Forecasting Methods2001
- Introduction to financial forecastingApplied Intelligence, 1996
- Diels‐alder reactions of 2‐ and 3‐vinyl‐1‐(phenylsulfonyl)pyrrolesJournal of Heterocyclic Chemistry, 1995
- Apples, oranges and mean square errorInternational Journal of Forecasting, 1988
- Empirical exchange rate models of the seventiesJournal of International Economics, 1983
- The accuracy of extrapolation (time series) methods: Results of a forecasting competitionJournal of Forecasting, 1982