Comparison of Classical Arima Forecasting Methods to the Machine Learning LSTM Method: a Case Study on DAX® 50 ESG Index

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F04274644%3A_____%2F25%3A%230001313" target="_blank" >RIV/04274644:_____/25:#0001313 - isvavai.cz</a>

Výsledek na webu

<a href="https://acta.vsfs.eu/pdf/acta-2025-1-03.pdf" target="_blank" >https://acta.vsfs.eu/pdf/acta-2025-1-03.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.37355/acta-2025/1-03" target="_blank" >10.37355/acta-2025/1-03</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Classical Arima Forecasting Methods to the Machine Learning LSTM Method: a Case Study on DAX® 50 ESG Index

Popis výsledku v původním jazyce

Background: Traditional econometric models like ARIMA, while foundational for time series forecasting, often rely on assumptions of linearity and stationarity. These models can fall short in capturing the complex, nonlinear dynamics frequently present in financial markets. This has led to the adoption of machine learning methods like Long Short- Term Memory (LSTM) networks, which are specifically designed to recognize long-term dependencies in sequential data, offering a p otential a dvantage i n m odeling v olatile financial time series. Aim: This study compares the predictive performance of a classical econometric model (ARIMA) with a deep learning approach (LSTM) in the context of stock index forecasting using the DAX 50 ESG index from 2020 to 2024. Methods: An autoregressive integrated moving average (ARIMA) model is compared against a long short-term memory (LSTM) neural network. The models are evaluated using both a static train-test split and a more rigorous expanding window forecast scheme. Predictive accuracy is measured by standard error metrics (MAE, RMSE, MAPE) and the Diebold-Mariano test. Results: The empirical results show that the LSTM model achieves lower forecast errors than the best-fitting A RIMA m odel i n b oth e valuation f rameworks. I n t he e xpanding window scenario (repeated retraining), the LSTM maintains a statistically significant, though modest, forecasting advantage over the ARIMA model. Originality/Value: The findings suggest that while the LSTM's ability to capture nonlinear patterns offers a f orecasting e dge, t he i mprovement i s i ncremental i n a h ighly l iquid and efficient market. This case study highlights the potential of deep learning methods in finance b ut a lso r einforces t he n otion t hat s trong m arket e fficiency can lim it the forecasting benefits of such complex models.

Název v anglickém jazyce

Comparison of Classical Arima Forecasting Methods to the Machine Learning LSTM Method: a Case Study on DAX® 50 ESG Index

Popis výsledku anglicky

Background: Traditional econometric models like ARIMA, while foundational for time series forecasting, often rely on assumptions of linearity and stationarity. These models can fall short in capturing the complex, nonlinear dynamics frequently present in financial markets. This has led to the adoption of machine learning methods like Long Short- Term Memory (LSTM) networks, which are specifically designed to recognize long-term dependencies in sequential data, offering a p otential a dvantage i n m odeling v olatile financial time series. Aim: This study compares the predictive performance of a classical econometric model (ARIMA) with a deep learning approach (LSTM) in the context of stock index forecasting using the DAX 50 ESG index from 2020 to 2024. Methods: An autoregressive integrated moving average (ARIMA) model is compared against a long short-term memory (LSTM) neural network. The models are evaluated using both a static train-test split and a more rigorous expanding window forecast scheme. Predictive accuracy is measured by standard error metrics (MAE, RMSE, MAPE) and the Diebold-Mariano test. Results: The empirical results show that the LSTM model achieves lower forecast errors than the best-fitting A RIMA m odel i n b oth e valuation f rameworks. I n t he e xpanding window scenario (repeated retraining), the LSTM maintains a statistically significant, though modest, forecasting advantage over the ARIMA model. Originality/Value: The findings suggest that while the LSTM's ability to capture nonlinear patterns offers a f orecasting e dge, t he i mprovement i s i ncremental i n a h ighly l iquid and efficient market. This case study highlights the potential of deep learning methods in finance b ut a lso r einforces t he n otion t hat s trong m arket e fficiency can lim it the forecasting benefits of such complex models.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

50200 - Economics and Business

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Acta VŠFS

ISSN

1802-792X

e-ISSN

—

Svazek periodika

19

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

21

Strana od-do

32-52

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—