Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and Bitcoins
This study analyzes the transmission of market uncertainty on key European financial markets and the cryptocurrency market over an extended period, encompassing the pre-, during, and post-pandemic periods. Daily financial market indices and price observations are used to assess the forecasting model...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Forecasting |
Subjects: | |
Online Access: | https://www.mdpi.com/2571-9394/5/2/26 |
_version_ | 1797594813083680768 |
---|---|
author | Apostolos Ampountolas |
author_facet | Apostolos Ampountolas |
author_sort | Apostolos Ampountolas |
collection | DOAJ |
description | This study analyzes the transmission of market uncertainty on key European financial markets and the cryptocurrency market over an extended period, encompassing the pre-, during, and post-pandemic periods. Daily financial market indices and price observations are used to assess the forecasting models. We compare statistical, machine learning, and deep learning forecasting models to evaluate the financial markets, such as the ARIMA, hybrid ETS-ANN, and <i>k</i>NN predictive models. The study results indicate that predicting financial market fluctuations is challenging, and the accuracy levels are generally low in several instances. ARIMA and hybrid ETS-ANN models perform better over extended periods compared to the <i>k</i>NN model, with ARIMA being the best-performing model in 2018–2021 and the hybrid ETS-ANN model being the best-performing model in most of the other subperiods. Still, the <i>k</i>NN model outperforms the others in several periods, depending on the observed accuracy measure. Researchers have advocated using parametric and non-parametric modeling combinations to generate better results. In this study, the results suggest that the hybrid ETS-ANN model is the best-performing model despite its moderate level of accuracy. Thus, the hybrid ETS-ANN model is a promising financial time series forecasting approach. The findings offer financial analysts an additional source that can provide valuable insights for investment decisions. |
first_indexed | 2024-03-11T02:27:48Z |
format | Article |
id | doaj.art-9a1e2338994342f69b3da43339375b4e |
institution | Directory Open Access Journal |
issn | 2571-9394 |
language | English |
last_indexed | 2024-03-11T02:27:48Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Forecasting |
spelling | doaj.art-9a1e2338994342f69b3da43339375b4e2023-11-18T10:25:43ZengMDPI AGForecasting2571-93942023-06-015247248610.3390/forecast5020026Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and BitcoinsApostolos Ampountolas0School of Hospitality Administration, Boston University, Boston, MA 02215, USAThis study analyzes the transmission of market uncertainty on key European financial markets and the cryptocurrency market over an extended period, encompassing the pre-, during, and post-pandemic periods. Daily financial market indices and price observations are used to assess the forecasting models. We compare statistical, machine learning, and deep learning forecasting models to evaluate the financial markets, such as the ARIMA, hybrid ETS-ANN, and <i>k</i>NN predictive models. The study results indicate that predicting financial market fluctuations is challenging, and the accuracy levels are generally low in several instances. ARIMA and hybrid ETS-ANN models perform better over extended periods compared to the <i>k</i>NN model, with ARIMA being the best-performing model in 2018–2021 and the hybrid ETS-ANN model being the best-performing model in most of the other subperiods. Still, the <i>k</i>NN model outperforms the others in several periods, depending on the observed accuracy measure. Researchers have advocated using parametric and non-parametric modeling combinations to generate better results. In this study, the results suggest that the hybrid ETS-ANN model is the best-performing model despite its moderate level of accuracy. Thus, the hybrid ETS-ANN model is a promising financial time series forecasting approach. The findings offer financial analysts an additional source that can provide valuable insights for investment decisions.https://www.mdpi.com/2571-9394/5/2/26hybrid ETS-ANN modelARIMA model<i>k</i>NN modeltime series forecastingcombination forecastingEuropean financial stock markets |
spellingShingle | Apostolos Ampountolas Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and Bitcoins Forecasting hybrid ETS-ANN model ARIMA model <i>k</i>NN model time series forecasting combination forecasting European financial stock markets |
title | Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and Bitcoins |
title_full | Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and Bitcoins |
title_fullStr | Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and Bitcoins |
title_full_unstemmed | Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and Bitcoins |
title_short | Comparative Analysis of Machine Learning, Hybrid, and Deep Learning Forecasting Models: Evidence from European Financial Markets and Bitcoins |
title_sort | comparative analysis of machine learning hybrid and deep learning forecasting models evidence from european financial markets and bitcoins |
topic | hybrid ETS-ANN model ARIMA model <i>k</i>NN model time series forecasting combination forecasting European financial stock markets |
url | https://www.mdpi.com/2571-9394/5/2/26 |
work_keys_str_mv | AT apostolosampountolas comparativeanalysisofmachinelearninghybridanddeeplearningforecastingmodelsevidencefromeuropeanfinancialmarketsandbitcoins |