Explainable AI and Causal Inference are some of the most vibrant areas in Machine Learning in recent years. This page explores the opportunities of combining those two areas.
Explainable AI (XAI) is artificial intelligence (AI) in which the results of the ML model can be interpreted by humans.
Causal inference is the process of determining the actual effect of a particular phenomenon (feature) that is a component of a complex system.
link: https://github.com/interpretml/DiCE
DiCE implements counterfactual (CF) explanations that provide this information by showing feature-perturbed versions of the same person who received the loan, e.g., you would have received the loan if your income was higher by $10,000. In other words, it provides "what-if" explanations for model output and can be a valuable complement to other explanation methods, both for end-users and model developers.
- Scott Cunningham, "Causal Inference: The Mixtape", 2021, https://mixtape.scunning.com/index.html
- Matheus Facure Alves, "Causal Inference for The Brave and True", 2021, https://matheusfacure.github.io/python-causality-handbook/landing-page.html
KDD 2021 Tutorial: Causal Inference and Machine Learning in Practice with EconML and CausalML: Industrial Use Cases at Microsoft, TripAdvisor, Uber https://github.com/causal-machine-learning/kdd2021-tutorial