English

Probabilities of Causation and Root Cause Analysis with Quasi-Markovian Models

Machine Learning 2025-09-03 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2509.02535,
  title  = {Probabilities of Causation and Root Cause Analysis with Quasi-Markovian Models},
  author = {Eduardo Rocha Laurentino and Fabio Gagliardi Cozman and Denis Deratani Maua and Daniel Angelo Esteves Lawand and Davi Goncalves Bezerra Coelho and Lucas Martins Marques},
  journal= {arXiv preprint arXiv:2509.02535},
  year   = {2025}
}

Comments

Accepted at the 35th Brazilian Conference on Intelligent Systems (BRACIS 2025)