0640435 20260224163713.720251025235959.9 105019109156 001602908700002 10.1016/j.eneco.2025.108988 16 s. P cav_un_epca*02504260140-9883152Elsevier Distributional forecasting Deep learning Probabilistic Electricity Energy time series cav_un_auth*0462008 Hanus Luboš UTIA-B Ekonometrie Department of Econometrics E E CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0242028 Baruník Jozef UTIA-B Ekonometrie Department of Econometrics E E Department of Econometrics CZ Ústav teorie informace a automatizace AV ČR, v. v. i. https://library.utia.cas.cz/separaty/2025/E/hanus-0640435.pdf https://www.sciencedirect.com/science/article/pii/S0140988325008187?via%3Dihub GA24-11555S GA ČR CZ cav_un_auth*0472836 We propose a novel machine learning approach for probabilistic forecasting of hourly day-ahead electricity prices. In contrast with the recent advances in data-rich probabilistic forecasting, which approximates distributions with few features (such as moments), our method is nonparametric and selects the distribution from all possible empirical distributions learned from the input data without the need for limiting assumptions. The model that we propose is a multioutput neural network that accounts for the temporal dynamics of the probabilities and controls for monotonicity using a penalty. Such a distributional neural network can precisely learn complex patterns from many relevant variables that affect electricity prices. We illustrate the capacity of the developed method on German hourly day-ahead electricity prices and predict their probability distribution via many variables, revealing new valuable information in the data. WOS AH 50000 50200 50202 2026 RVO:67985556 https://hdl.handle.net/11104/0371248 S 108988 C ECONOMICS 13.2 2.6 3.8 0.04634 2.28 53243 230 3.919 64.57 15.43 27784 Q1 12.300 747 Q1 99.9 4.59 Q1 99.9 2025 105019109156 SCOPUS PUBMED 001602908700002 WOS cav_un_epca*0250426 Energy Economics 152 1 2025 0140-9883 1873-6181 Elsevier