Skip to content

Publications & Papers

Peer-Reviewed Publications

2025

"Stable structure learning with HC-Stable and Tabu-Stable algorithms"

  • International Journal of Approximate Reasoning
  • Introduces Tabu-Stable, a novel score-based Bayesian Network structure learning algorithm that eliminates instability due to variable ordering, achieving consistent and superior performance across datasets and variable types
  • Paper | Code

"Decoding the mechanisms of the Hattrick football manager game using Bayesian network structure learning for optimal decision-making" (Under Review)

  • Entertainment Computing
  • This paper applies Bayesian Network structure learning to uncover and model the hidden mechanics of the online football manager game Hattrick, combining data and domain knowledge to explain and simulate game behaviour.
  • Preprint

"Causal discovery using dynamically requested knowledge"

  • Knowledge-Based Systems
  • Introduces a dynamic knowledge integration approach for Causal Bayesian Network learning, where the algorithm actively requests expert input during learning, improving structural accuracy and transparency over existing methods.
  • Paper | Code

"Using GPT-4 to guide causal machine learning"

  • Expert Systems with Applications
  • Evaluating GPT-4’s ability to infer causal relationships from variable labels alone shows it produces expert-like causal graphs and, when combined with causal ML, improves data-driven causal discovery accuracy and trustworthiness.
  • Paper

"Investigating potential causes of Sepsis with Bayesian network structure learning"

  • Applied Intelligence
  • Combining hospital data with clinical expertise, this study uses Bayesian Network structure learning and model averaging to identify causal risk factors for Sepsis, revealing policy-relevant relationships and achieving strong predictive performance.
  • Paper

Past years to be completed

Conference Presentations

2024

Journal Reviewing

*To be completed *

Conference Reviewing

  • PGM (2026)

Current Collaborations

  • Queen Mary University of London: Host institution for research visit

This publication record reflects a commitment to rigorous, reproducible research at the intersection of causal inference and artificial intelligence, with emphasis on practical applications and open science principles.