AI Forecasting of Green Hydrogen Financial Performance: Prophet vs. ARIMA
Abstract: Green hydrogen (H₂V) is central to the energy transition, yet financial forecasting for the sector remains understudied. This study compares Prophet and ARIMA for forecasting the Global X Hydrogen ETF (HYDR), a capital-market proxy for the sector, using 1,045 daily observations (Oct/2021–Nov/2025). Granger tests found no robust predictive power of crude oil (CL=F) or the global market (URTH) over HYDR, so both were excluded as regressors. ARIMA(2,1,1) outperformed Prophet on all metrics (MAPE 22.39% vs. 34.63%), showing that classical models suit short, volatile emerging-sector series better than Prophet. Keywords: Green Hydrogen, Prophet Model, ARIMA; Granger Causality, ETF HYDR.
Authors
- Emanuel da Cruz Lima (ORCID: https://orcid.org/0000-0003-0146-2138)
- Eder Johnson de Area Leão Pereira
- Thanmillys Nadhynne de Lima da Conceição
Institutions
- Instituto Federal do Maranhão (BR)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-12
- DOI
- https://doi.org/10.5281/zenodo.24168844
- Primary Topic
- Stock Market Forecasting Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00