Souhaib Ben Taieb
Associate Professor of Statistics and Data Science
Research interests
Professor Ben Taieb’s research encompass a wide range of topics within AI and statistics, including probabilistic machine learning, uncertainty quantification, time series analysis and forecasting, anomaly detection, forecast scoring, and calibration. His work aims to capture subtle statistical properties in dynamic data, such as nonlinear cross-temporal dependencies, complex seasonal patterns, time-varying uncertainty, intermittency, and heterogeneity. Email
Prior to joining MBZUAI, Professor Ben Taieb was Associate Professor of Machine Learning at the University of Mons (UMONS) in Belgium, where he led the Big Data and Machine Learning Lab. Before that he served as a lecturer in Business Analytics in the Department of Econometrics and Business Statistics at Monash University in Melbourne, which he joined after a postdoctoral research fellowship in the Spatio-Temporal Statistics and Data Science group at KAUST in Saudi Arabia.
Professor Ben Taieb has won various research grants in academia and through industry collaborations, including joint research with Huawei, John Cockerill, and Ion Beam Applications. He received a Doctoral Research Fellowship from the Belgian National Fund for Scientific Research and was awarded the Solvay Award for the best Ph.D. thesis. He is currently associate editor of the International Journal of Forecasting and regularly reviews for leading machine learning conferences and statistics journals.
- Postdoc in Statistics, King Abdullah University of Science and Technology (KAUST), Saudi Arabia.
- Ph.D. in Computer Science (Machine Learning), Free University of Brussels, Belgium.
- Master’s in Computer Science, Free University of Brussels, Belgium.
- Top 33% Reviewer, International Conference on Machine Learning 2020.
- Huawei Research Innovation Grant, 2017.
- Early Career Faculty Research Grant, Monash University, 2016.
- Best Contributed Submission, Machine Learning and Data Analytics 2015, Doha, Qatar.
- Solvay prize for best PhD thesis, 2014.
- IEEE Power & Energy Society Award, Global Energy Forecasting Competition 2012.
- Solvay prize for best Master's thesis, 2009.
- Doctoral Research Fellowship, Belgian National Fund for Scientific Research, 2009.
- Meng, X., Taylor, J. W., Ben Taieb, S., Li, S.: “Scores for multivariate distributions and level sets”, Operations Research, 2023.
- Dheur, V., Bosser, T., Izbicki, R., & Ben Taieb, S.: “Distribution-free conformal joint prediction regions for neural marked temporal point processes”, Machine Learning, 2024.
- Ben Taieb, S., Taylor, J. W., & Hyndman, R. J.: “Hierarchical probabilistic forecasting of electricity demand with smart meter data”, Journal of the American Statistical Association, 2020.
- Dheur, V., & Ben Taieb, S.: “Probabilistic calibration by design for neural network regression”, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, 2024.
- Hien, L. T. K., Patra, S., & Ben Taieb, S.: “Anomaly detection with semi-supervised classification based on risk estimators”, Transactions on Machine Learning Research, 2024.
- Ben Taieb, S., Yu, J., Barreto, M. N., & Rajagopal, R.: “Regularization in hierarchical time series forecasting with application to electricity smart meter data”, Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017.