New Q1 paper: Classical to Generative AI for Time Series Forecasting (Finance, Energy, Health)
I am glad to share the publication of our new research article with my co-authors: Mohamed Nachat, Said El Melhaoui, Moustapha Faizi, Mohamed Fihri, Raby Guerbaz, and Salah-Eddine El Adlouni:
“From classical to generative AI approaches for univariate and multivariate time series forecasting with an evaluation in finance, energy, and health domains”
Published in Discover Artificial Intelligence (Q1, Scopus-indexed).
The study provides a cross-domain comparison of classical statistical methods, machine learning, deep learning, and generative AI approaches for time series forecasting across finance, energy, and health applications.
As a co-supervisor, I am particularly proud of our PhD student Mohamed Nachat for this excellent work and his valuable contribution to the research. Congratulations, Mohamed — great work, and keep going! The best is yet to come.
Many thanks to all my co-authors for this fruitful collaboration.
DOI: https://doi.org/10.1007/s44163-026-01866-0
ResearchGate: https://www.researchgate.net/publication/413555081_From_classical_to_generative_AI_approaches_for_univariate_and_multivariate_time_series_forecasting_with_an_evaluation_in_finance_energy_and_health_domains
I am an Assistant Professor of Statistics and Applied Mathematics at Mohammed First University of Oujda, Morocco. My research focuses on statistical modeling, econometrics, and financial time series forecasting, with interests in stochastic processes, machine learning, deep learning, and generative models. I publish in peer-reviewed journals indexed in Scopus and Web of Science, combining theoretical and applied research in finance, insurance, Healthcare, Social Sciences, and data analytics.