Causal machine learning for decisions that matter
From marketing strategy to healthcare innovation, my work explores how multimodal representations and Double Machine Learning make causal insights more actionable.
Working papers
Rigorous inquiries that push causal inference, multimodal learning, and empirical economics forward.
Adventures in Demand Analysis Using AI
Philipp Bach, Victor Chernozhukov, Sven Klaassen, Martin Spindler, Jan Teichert-Kluge, Suhas Vijaykumar
We integrate text, imagery, and tabular signals into transformer-based embeddings to model product demand. The result: sharper estimates of price elasticity and new perspectives on heterogeneity.
DoubleMLDeep: Estimation of Causal Effects with Multimodal Data
Sven Klaassen, Jan Teichert-Kluge, Philipp Bach, Victor Chernozhukov, Martin Spindler, Suhas Vijaykumar
Introduces a neural architecture tailored to DoubleML and a semi-synthetic benchmark for studying text & image confounders. Demonstrates measurable gains in causal estimation quality.
Talks & keynotes
Sharing methods and lessons from deploying causal ML in the wild.
DoubleMLDeep: Estimation of Causal Effects with Multimodal Data
How DoubleML can embrace text and imagery for more reliable treatment effect estimation, backed by new datasets and open-source tools.
Econometric Society ESIF AIML · Cornell University · 2024
Estimating Price Elasticities with Text and Images
Extending the DML framework to multimodal confounding with applications to e-commerce pricing. Demonstrates uplift from embedding-based representations.
University of Queensland · Econometrics Colloquium · 2024
Estimating Price Elasticities with Text and Images
Explores a unified workflow for price elasticity estimation using multimodal data with DoubleML, featuring empirical benchmarks and reproducible examples.
Australian National University · Computational Economics Workshop · 2024
Price Elasticity Estimation using Image and Text Data
Highlights methodological advances and case studies for causal inference with unstructured data, motivating future DoubleML extensions.
Causal Data Science Meeting · 2023
Other publications
Causal Machine Learning with Deep Learning approaches using the DoubleML Framework
Moritz Sundermann, Jan Teichert-Kluge
An object-oriented implementation that merges deep learning with DoubleML, validated through simulation studies and a real-world case study.