Cause Effect Pairs in Machine Learning

This book presents ground-breaking advances in the domain of causal structure learning. The problem of distinguishing cause from effect (“Does altitude cause a change in atmospheric pressure, or vice versa?”) is here cast as a binary classification problem, to be tackled by machine learning algorithms.  Based on the results of the ChaLearn Cause-Effect Pairs Challenge, this book reveals that the joint distribution of two variables can be scrutinized by machine learning algorithms to reveal the possible existence of a “causal mechanism”, in the sense that the values of one variable may have been generated from the values of the other.  

1. The cause-effect problem: motivation, ideas, and popular misconceptions.- 2. Evaluation methods of cause-effect pairs.- 3. Learning Bivariate Functional Causal Models.- 4. Discriminant Learning Machines.- 5. Cause-Effect Pairs in Time Series with a Focus on Econometrics.- 6. Beyond cause-effect pairs.- 7. Results of the Cause-Effect Pair Challenge.- 8. Non-linear Causal Inference using Gaussianity Measures.- 9. From Dependency to Causality: A Machine Learning Approach.- 10. Pattern-based Causal Feature Extraction.- 11. Training Gradient Boosting Machines using Curve-fitting and Information-theoretic Features for Causal Direction Detection.- 12. Conditional distribution variability measures for causality detection.- 13. Feature importance in causal inference for numerical and categorical variables.- 14. Markov Blanket Ranking using Kernel-based Conditional Dependence Measures.