My research focuses mainly on applied micro in Empirical IO & Health, using causal machine learning and structural IO to measure heterogeneous own- and cross-price elasticities and to evaluate pricing and welfare in pharmaceutical markets. Methodologically, I adopted Neyman-orthogonal DML/IV for continuous treatments with cross-fitting on high-dimensional panels and multi-product pricing to recover marginal costs and run Ramsey/Boiteux counterfactuals. I also study innovation responses to demand shocks (e.g., safety recalls) to quantify market-size elasticities in the Pharmaceutical. Complementary work in ML theory (orthogonalized learners, optimal data collection) in health economics and production networks was pursued to strengthen identification, feature construction, and cross-product interaction modeling required by my IO agenda.