Interpretable Machine Learning through Mathematical Frameworks of Explainable Artificial Intelligence (XAI)

Ejiro Stanley Omokoh *

Department of Mathematics, Western Delta University Oghara, Delta State, Nigeria.

Omamoke O. E. Enaroseha

Department of Physics, Delta State University Abraka, Delta State, Nigeria.

Atomatofa Emmanuel Oghenero

Department of Cyber Security, Federal University of Technology, Owerri, Nigeria.

Patience Oghenedoro Omokoh

Department of Science Laboratory Technology, Delta State Polytechnic Ogwashi-uku, Nigeria.

*Author to whom correspondence should be addressed.


Abstract

The rapid integration of Artificial Intelligence (AI) across healthcare, finance, governance, and other high-stakes sectors necessitates robust mechanisms for transparency, accountability, and trust. Explainable Artificial Intelligence (XAI) addresses this need by providing methods to make model decisions understandable to humans. This paper develops mathematical frameworks that embed interpretability into machine learning models, focusing on symbolic logic, causal inference, probabilistic graphical models, and formal measures of explanation. We review and synthesise existing XAI techniques such as LIME and SHAP, critique their strengths and limitations, and propose a hybrid neuro-symbolic approach that integrates rule-based symbolic reasoning with statistical learning. A detailed healthcare case study demonstrates how the framework yields transparent diagnostic rules, preserves predictive performance, and enhances clinician trust. We conclude with a discussion on scalability, fairness-aware explainability, and directions for future research.

Keywords: Artificial Intelligence, mathematical frameworks, interpretable machine learning


How to Cite

Omokoh, Ejiro Stanley, Omamoke O. E. Enaroseha, Atomatofa Emmanuel Oghenero, and Patience Oghenedoro Omokoh. 2025. “Interpretable Machine Learning through Mathematical Frameworks of Explainable Artificial Intelligence (XAI)”. Asian Journal of Pure and Applied Mathematics 7 (1):701-8. https://doi.org/10.56557/ajpam/2025/v7i1234.

Downloads

Download data is not yet available.