ABSTRACT
In recent years, both academic research and industry applications see an increased effort in using machine learning methods to measure granular causal effects and design optimal policies based on these causal estimates. Open source packages such as CausalML and EconML provide a unified interface for applied researchers and industry practitioners with a variety of machine learning methods for causal inference. The tutorial will cover the topics including conditional treatment effect estimators by meta-learners and tree-based algorithms, model validations and sensitivity analysis, optimization algorithms including policy leaner and cost optimization. In addition, the tutorial will demonstrate the production of these algorithms in industry use cases.
- Huigang Chen, Totte Harinen, Jeong-Yoon Lee, Mike Yung, and Zhenyu Zhao. 2020. Causalml: Python package for causal machine learning. arXiv preprint arXiv:2002.11631 (2020).Google Scholar
- Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo, Christian Hansen, and Whitney Newey. 2017. Double/debiased/neyman machine learning of treatment effects. American Economic Review , Vol. 107, 5 (2017), 261--65.Google ScholarCross Ref
- Susan Gruber and Mark J Van Der Laan. 2009. Targeted maximum likelihood estimation: A gentle introduction. (2009).Google Scholar
- Jason Hartford, Greg Lewis, Kevin Leyton-Brown, and Matt Taddy. 2017. Deep IV: A flexible approach for counterfactual prediction. In International Conference on Machine Learning. PMLR, 1414--1423.Google Scholar
- Edward H Kennedy. 2020. Optimal doubly robust estimation of heterogeneous causal effects. arXiv preprint arXiv:2004.14497 (2020).Google Scholar
- Sören R Künzel, Jasjeet S Sekhon, Peter J Bickel, and Bin Yu. 2019. Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the national academy of sciences , Vol. 116, 10 (2019), 4156--4165.Google ScholarCross Ref
- Greg Lewis and Vasilis Syrgkanis. 2020. Double/Debiased Machine Learning for Dynamic Treatment Effects. arXiv preprint arXiv:2002.07285 (2020).Google Scholar
- Christos Louizos, Uri Shalit, Joris Mooij, David Sontag, Richard Zemel, and Max Welling. 2017. Causal effect inference with deep latent-variable models. arXiv preprint arXiv:1705.08821 (2017).Google Scholar
- Microsoft Research. 2019. EconML: A Python Package for ML-Based Heterogeneous Treatment Effects Estimation . https://github.com/microsoft/EconML. Version 0.x.Google Scholar
- Piotr Rzepakowski and Szymon Jaroszewicz. 2012. Decision trees for uplift modeling with single and multiple treatments. Knowledge and Information Systems , Vol. 32, 2 (2012), 303--327.Google ScholarCross Ref
- Fung Po Tso, Lin Cui, Lizhuo Zhang, Weijia Jia, Di Yao, Jin Teng, and Dong Xuan. 2013. DragonNet: a robust mobile internet service system for long-distance trains. IEEE transactions on mobile computing , Vol. 12, 11 (2013), 2206--2218.Google Scholar
- Stefan Wager and Susan Athey. 2018. Estimation and inference of heterogeneous treatment effects using random forests. J. Amer. Statist. Assoc. , Vol. 113, 523 (2018), 1228--1242.Google ScholarCross Ref
Index Terms
- Causal Inference and Machine Learning in Practice with EconML and CausalML: Industrial Use Cases at Microsoft, TripAdvisor, Uber
Recommendations
Inference in multi-agent causal models
In this article, we demonstrate the usefulness of causal Bayesian networks as probabilistic reasoning systems. The biggest advantage of causal Bayesian networks over traditional probabilistic Bayesian networks is that they sometimes allow to perform ...
Causal inference through a witness protection program
One of the most fundamental problems in causal inference is the estimation of a causal effect when treatment and outcome are confounded. This is difficult in an observational study, because one has no direct evidence that all confounders have been ...
Disentangling causality: assumptions in causal discovery and inference
AbstractCausality has been a burgeoning field of research leading to the point where the literature abounds with different components addressing distinct parts of causality. For researchers, it has been increasingly difficult to discern the assumptions ...
Comments