Join our Brown Bag Data Science Lab for an engaging discussion with Philipp Bach, Assistant Professor at Freie Universität Berlin.
Abstract from the speaker:
In this talk, we explore the integration of unstructured, multimodal data – specifically text and images – into causal inference and treatment effect estimation. We highlight the challenges and opportunities presented by combining these non-traditional data sources with causal analysis, and outline potential solution strategies. Focusing on the statistical approach of Double Machine Learning, our talk showcases a real-world application using demand estimation data from Amazon.com. By leveraging modern deep learning models, we unify text descriptions, images, and tabular covariates to create rich product representations that capture subtle attributes such as product quality, branding, and other characteristics. We demonstrate how these embeddings can be exploited to estimate heterogeneous price elasticities, offering a more nuanced understanding of consumer behavior.
Links to the related papers:
About the speaker:
Philipp Bach is an Assistant Professor of Econometrics at the Department of Economics at the Freie Universität Berlin. Before, he was a Postdoctoral Researcher and PhD student at the University of Hamburg. His research focuses on statistical methods for causal machine learning and their software implementation. Bach applies these methods mainly in the context of economic research questions.
Currently, Philipp Bach is working on projects on sensitivity analysis for causal ML, double machine learning for difference-in-differences models and causal inference based on multimodal, unstructured data like images and text.
Bring your own lunch bag! Light pastries and drinks will be available in case you forget to bring it.
—
The Data Science Brown Bag Series is an informal and interactive gathering where participants bring their own brown bag lunch and engage in discussions on research and insights the field of data and computational social science (light pastries and drinks will be available if you forget your lunch bag!).
The series provides a platform for data enthusiasts, researchers, and practitioners to share their experiences, best practices, and emerging methodologies and research in using data science to analyze and understand social and political phenomena. The brown bag talk series is for anyone interested in data science and social science to network, learn, and share ideas in a casual and friendly setting.
