Program Focus
This program focuses primarily on methodological training: Python programming and data management, forecasting and prediction, and causal inference for questions relevant to economic and social policy. Participants learn to build reproducible workflows and apply modern quantitative tools to real policy questions, with one module dedicated to how evidence is interpreted, communicated, and governed in real policy settings, including fairness, transparency, and accountability.
What you will be able to do
Build and evaluate forecasting models and communicate uncertainty
Apply causal inference logic to policy evaluation questions
Apply machine learning took to address causality and forecasting
Work with unstructured text and (introductory) image data workflows using modern AI tools
Communicate findings responsibly to decision-makers, including ethical trade-offs
Program structure (4 modules)
Python programming and data wrangling (pandas, EDA, visualisation, reproducibility)
Forecasting and causal inference for policy (prediction vs causality, evaluation designs)
Neural networks and unstructured data (text analytics, LLM workflows, responsible AI)
From data to policy (interpretability, accountability, communication and governance)
Assessment and UNU certificate
Short online assignments during the program.
Final applied deliverable (project/policy brief/memo, for the different modules).
A UNU Certificate of Completion is awarded upon successful completion of required assessments
Optional visiting period in Bruges (Belgium)
Participants may apply for an on-site visiting period at UNU-CRIS (Bruges) to join seminars, receive mentorship, and build networks.
Places are limited and subject to selection.
Application
To apply, submit your CV by email to info-mep@cris.unu.edu