A0211
Title: DoubleMLDeep: Estimation of causal effects with multimodal data
Authors: Martin Spindler - University of Hamburg (Germany) [presenting]
Abstract: The use of unstructured, multimodal data, namely text and images, is explored in causal inference and treatment effect estimation. We propose a neural network architecture that is adapted to the double machine learning (DML) framework, specifically the partially linear model. An additional contribution is a new method to generate a semi-synthetic dataset, which can be used to evaluate the performance of causal effect estimation in the presence of text and images as confounders. The proposed methods and architectures are evaluated on the semi-synthetic dataset and compared to standard approaches, highlighting the potential benefit of using text and images directly in causal studies. Our findings have implications for researchers and practitioners in economics, marketing, finance, medicine and data science in general who are interested in estimating causal quantities using non-traditional data.
