Probabilities of Causation and Root Cause Analysis with Quasi-Markovian Models
By: Eduardo Rocha Laurentino , Fabio Gagliardi Cozman , Denis Deratani Maua and more
Potential Business Impact:
Finds the main reason for problems.
Probabilities of causation provide principled ways to assess causal relationships but face computational challenges due to partial identifiability and latent confounding. This paper introduces both algorithmic simplifications, significantly reducing the computational complexity of calculating tighter bounds for these probabilities, and a novel methodological framework for Root Cause Analysis that systematically employs these causal metrics to rank entire causal paths.
Similar Papers
Probabilistic Modelling is Sufficient for Causal Inference
Machine Learning (Stat)
Answers "why" questions using only probability.
Searching for actual causes: Approximate algorithms with adjustable precision
Artificial Intelligence
Finds the real reasons why things happen.
Estimating Probabilities of Causation with Machine Learning Models
Artificial Intelligence
Helps predict why things happen with less data.