Euro Area Business Cycle Network Training School
Techniques for Big Data and Machine Learning Analysis for Central Banks by Gianluca Bontempi (Universite Libre de Bruxelles) & Michele Lenza (European Central Bank)
13 - 15 October 2026
In-person in EDHEC Nice, France
General Description
We are pleased to announce details of the latest EABCN Training School; a three-day course entitled “Techniques for Big Data and Machine Learning Analysis for Central Banks”. Gianluca Bontempi (Université Libre de Bruxelles) & Michele Lenza (European Central Bank) will teach the course. It is primarily aimed at participants in the Euro Area Business Cycle Network but applications will also be considered from doctoral students, post-doctoral researchers and economists working in central banks and government institutions outside of the network, as well as commercial organisations (fees are applicable for non-network non-academic organisations).
Tentative course outline
This course presents an overview of the main AI and machine learning techniques, with a specific focus on tree-based methods and neural networks (with a particular emphasis on deep learning) that are increasingly used in economic analysis. It also discusses how these techniques can handle data types beyond traditional numerical inputs, including text and other unstructured sources. Then, it examines a series of empirical applications which are relevant for macroeconomic analysis and policy, including methods for capturing non-linearities in economic relationships, conducting risk analysis, and incorporating non-traditional data into forecasting models.
Day 1 - Tuesday, October 13th, 2026
Morning Lecture Session 1 (09:30 - 13:00):
From Linear Models to Tree‑Based Models, Theory, Estimation, and Applications
- Instructor: Gianluca Bontempi
Afternoon Lecture Session 2 (14:30 - 17:00):
From Shallow to Deep Learning: Introduction to Neural Networks and their Applications
- Instructor: Gianluca Bontempi
Day 2 - Wednesday, October 14th, 2026
Morning Lecture Session 3 (09:30 - 13:00):
Beyond Structured Numerical Data: Learning from Text: from n‑grams to Large Language Models
- Instructor: Gianluca Bontempi
Afternoon Lecture Session 4 (14:30 - 17:00):
Quantile regression forests for the analysis of the risks surrounding the inflation outlook, theory and practical application
- Instructor: Michele Lenza
Day 3 - Thursday, October 15th, 2026
Morning Lecture Session 5 (09:30 - 13:00):
Advanced Topics with tree- based methods, theory and practical application
- Instructor: Michele Lenza
Afternoon Lecture Session 6 (14:30 - 17:00):
Empirical Applications of Neural Networks
- Instructor: Michele Lenza
Software Requirements:
- Individual laptops with R and Python installed.
- Participants will not be required to run the code during the session. The code will be discussed to illustrate the practical applications. However, having the software installed may be useful for those who wish to experiment with the routines after the class.
Pre-requisite:
- A general familiarity with time-series econometrics is assumed.
Administrative Information
The deadline to submit has passed and we are no longer accepting any applications.
The course will take place in Nice, France at EDHEC. More information about logistics will be circulated closer to the date.
Participants will be invited to make their own arrangements regarding their travel, accommodation and meals. Further information about hotel options will be available to successful applicants.
Participants from non-academic institutions where the employer is not a member of the EABCN network are charged a course fee of €2500.
If you have any questions regarding the logistical details please contact Jemila Benchikh, CEPR Senior Events Officer at [email protected] with the subject line '5120- EABCN Training School -Bontempi & Lenza - Nice, 2026' .
About the Instructors:
Gianluca Bontempi is Full Professor in the Computer Science Department at the Université Libre de Bruxelles (ULB), Brussels, Belgium, co-head of the ULB Machine Learning Group (mlg.ulb.ac.be) and Walloon Excellence Research Institute (WEL-RI) investigator. He has been Director of (IB)2, the ULB/VUB Interuniversity Institute of Bioinformatics in Brussels (ibsquare.be) in 2013-17. His main research interests are big data mining, machine learning, bioinformatics, causal inference, predictive modelling and their application to complex tasks in engineering (time series forecasting, fraud detection) and life science (network inference, gene signature extraction). He was a Marie Curie fellow researcher, he was awarded in two international data analysis competitions, and he took part in many research projects in collaboration with universities and private companies all over Europe. He is the author of over 250 scientific publications and 2 patents, and his H-number is 69. He has been the Belgian (French Community) president of the TRAIL initiative, co-leader of the CLAIRE COVID-19 Task Force, associate editor of the International Journal of Forecasting and an IEEE Senior Member. He is also a co-author of several open-source software packages for bioinformatics, data mining and prediction.
Michele Lenza is Head of the Monetary Policy Research Division of the European Central Bank. He received a Ph.D. in Economics and Statistics from the Université Libre de Bruxelles and he is a Fellow of the Centre for Economic Policy Research (CEPR), the International Association for Applied Econometrics (IAAE) and the Euro Area Business Cycle Network. His research interests cover monetary economics, business cycle analysis and macro econometric methods. His research appeared in peer-reviewed journals, such as Econometrica, the Journal of the American Statistical Association, the Journal of Econometrics, The Review of Economics and Statistics, the Journal of the European Economic Association and the Economic Journal, among others.