0456185 20240103211849.120160229235959.9 84960075958 000374811000017 10.1016/j.eswa.2016.02.008 36 s. P cav_un_epca*02529430957-4174551 (2016)222-242Elsevier artificial neural networks realized volatility multiple-step-ahead forecasts energy markets cav_un_auth*0242028 Ekonometrie Department of Econometrics E E Department of Econometrics 50 Baruník Jozef UTIA-B A Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0327877 Ekonometrie Department of Econometrics E E Department of Econometrics 50 Křehlík Tomáš UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2016/E/barunik-0456185.pdf cav_un_auth*0281000 GBP402/12/G097 GA ČR CZ The popularity of realized measures and various linear models for volatility forecasting has been the focus of attention in the literature addressing energy markets' price variability over the past decade. However, there are no studies to help practitioners achieve optimal forecasting accuracy by guiding them to a specific estimator and model. This paper contributes to this literature in two ways. First, to capture the complex patterns hidden in linear models commonly used to forecast realized volatility, we propose a novel framework that couples realized measures with generalized regression based on artificial neural networks. Our second contribution is to comprehensively evaluate multiple-step-ahead volatility forecasts of energy markets using several popular high frequency measures and forecasting models. We compare forecasting performance across models and across realized measures of crude oil, heating oil, and natural gas volatility during three qualitatively distinct periods: the pre-crisis period, the 2008 global financial crisis, and the post-crisis period. AH 2017 2 4 A hod 4ah 20231122141530.1 RVO:67985556 http://hdl.handle.net/11104/0260445 cav_un_auth*0308308 Institute of Economic Studies, Faculty of Social Sciences, Charles University in Prague IES FSV UK CZ 1 Department of Econometrics UTIA-B 50200 OPERATIONS RESEARCH & MANAGEMENT SCIENCE S 2 Article Computer Science Artificial Intelligence|Engineering Electrical Electronic|Operations Research Management Science COMPUTERSCIENCE.ARTIFICIALINTELLIGENCE|ENGINEERING.ELECTRICAL&ELECTRONIC|OPERATIONSRESEARCH&MANAGEMENTSCIENCE 3.526 0.771 5.4 0.0548 0.719 31192 1.343 Q1 3.376 630 Q1 60.017 90 Q2 Q1 96.988 2016 Soubory v repozitáři: barunik-0456185.pdf 84960075958 SCOPUS 000374811000017 WOS cav_un_epca*0252943 Expert Systems With Applications 0957-4174 1873-6793 Roč. 55 č. 1 2016 222 242 Elsevier