Sven Klaassen, Jan Teichert-Kluge, Philipp Bach, Victor Chernozhukov, Martin Spindler, Suhas Vijaykumar
arXiv 1 Feb 2024 · Machine Learning · 2 citations (OpenAlex)
arXiv:2402.01785 · PDF · DOI · OpenAlex · Extracted main text
This paper explores the use of unstructured, multimodal data, namely text and images, 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 of our paper 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.
appendix boundary found by appendix_command · 97% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C… (2018) Double/debiased machine learning for treatment and structural parameters self | 0.874 | 5 | 2 | 100% |
| 2 | Somepalli, G., Goldblum, M., Schwarzschild, A., Bruss, C. B., and Go… (2021) Saint: Improved neural networks for tabular data via row attention and contrastive pre-training, 2021 | 0.644 | 2 | 2 | 100% |
| 3 | Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A.,… (2020) Transformers: State-of-the-art natural language processing | 0.644 | 2 | 2 | 100% |
| 4 | Miller, S., Howard, J., Adams, P., Schwan, M., and Slater, R (2021) Multi-modal classification using images and text | 0.511 | 2 | 1 | 100% |
| 5 | Bickel, P. J., Ritov, Y., and Tsybakov, A. B Simultaneous analysis of Lasso and Dantzig selector | 0.405 | 1 | 1 | 100% |
| 6 | Sridhar, D. and Blei, D. M (2022) Causal inference from text: A commentary | 0.405 | 1 | 1 | 100% |
| 7 | Feder, A., Keith, K. A., Manzoor, E., Pryzant, R., Sridhar, D., Wood… (2022) Causal inference in natural language processing: Estimation, prediction, interpretation and beyond | 0.405 | 1 | 1 | 100% |
| 8 | Foster, D. J. and Syrgkanis, V (2023) Orthogonal statistical learning | 0.405 | 1 | 1 | 100% |
| 9 | Goodfellow, I., Bengio, Y., and Courville, A (2016) Deep Learning | 0.405 | 1 | 1 | 100% |
| 10 | Jerzak, C. T., Johansson, F., and Daoud, A (2023) Estimating causal effects under image confounding bias with an application to poverty in africa, 2023a | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 46 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.