AI-Powered Econometric Forecasting & Causal Inference

Aim

Workshop Objectives

Workshop Structure

📊 Day 1 — Data Architecture & Causal ML Foundations

• Focus: Building rigorous empirical foundations for economic and policy analysis
• Foundations of causal inference in observational economic research; panel data structures and identification challenges; missing macroeconomic data and Multiple Imputation by Chained Equations (MICE)
• Hands-On:
  • Constructing and harmonizing multi-source panel datasets (World Bank & macroeconomic indicators)
  • Implementing MICE for macroeconomic datasets in Python
  • Feature engineering for temporal and policy-related financial indicators

💹 Day 2 — Advanced Causal Inference for Policy & Market Impact

• Focus: Estimating credible and heterogeneous economic policy effects
• Theoretical foundations of Double Machine Learning (DML), Causal Forests for heterogeneous treatment effects, and Synthetic Control using Bayesian Structural Time Series
• Hands-On:
  • Implementing DML for treatment effect estimation using EconML
  • Building and interpreting Causal Forest models for regional economic impact
  • Applying Synthetic Control methods for policy comparison analysis
  • Conducting robustness checks and model diagnostics

📈 Day 3 — Policy Simulation & Publication-Ready Financial Analytics

• Focus: Translating causal findings into actionable economic insights
• Best practices for reporting heterogeneous effects; interpreting SHAP values; communicating counterfactual results to academic and policy audiences
• Hands-On:
  • Building interactive economic policy dashboards using Streamlit
  • Developing counterfactual policy simulation tools
  • Generating publication-grade coefficient plots and economic trend visualizations using Plotly
  • Exporting reproducible outputs suitable for high-impact journals and grant proposals

Who Should Enrol?

Important Dates

Workshop Outcomes