An Explainable Machine Learning Framework for Political Instability Prediction and Early Warning Using Decision Tree Learning

• Author(s): Olatunde David Akinrolabu; Samuel Ohirenume Afekhiku; Victor Olumide Otokiti; Ayodeji Olusegun Akinwumi; Omambala Divine; Omojola Tomiwa Yusuf
• Paper ID: 1719457
• Page: 252-260
• Published Date: 03-07-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 10 Issue 1 July-2026

Abstract

It is common knowledge that political instability retards the development and progress of a country. Conflict and war have been the focus of extensive research throughout history. Certain factors can reliably predict conflict, including average income, political instability, low economic growth rates, and other socio-economic indicators. Machine learning can be used to predict many things, such as stock values, weather, movie preferences, and, as is the case for this project, a country’s political instability. This study presents a Decision Tree classifier trained on an integrated dataset compiled from the Centre for Systemic Peace (CSP) and the Fund for Peace (FFP), consisting of 1,778 records and 16 attributes. After preprocessing and integration, the dataset was split into training (70%) and test (30%) partitions. The implementation, built with Python’s scikit-learn library, achieves 97% classification accuracy, 98.5% precision, 98.5% recall, 99% F1-score on the test set, successfully categorising countries into high-risk (class 0) and low-risk (class 1) groups for political instability. A simple decision rule based on the mean fragility score (threshold ≈8.9) was extracted from the trained tree, offering an interpretable early-warning indicator. The model demonstrates the applicability of supervised machine learning to conflict prediction and early-warning systems for policymakers.

Keywords

Political Instability, Machine Learning, Conflict Prediction, Feature Selection, Decision Tree, Fragility Index.

Citations

IRE Journals:
Olatunde David Akinrolabu, Samuel Ohirenume Afekhiku, Victor Olumide Otokiti, Ayodeji Olusegun Akinwumi, Omambala Divine; Omojola Tomiwa Yusuf "An Explainable Machine Learning Framework for Political Instability Prediction and Early Warning Using Decision Tree Learning" Iconic Research And Engineering Journals Volume 10 Issue 1 2026 Page 252-260 https://doi.org/10.64388/IREV10I1-1719457

IEEE:
Olatunde David Akinrolabu, Samuel Ohirenume Afekhiku, Victor Olumide Otokiti, Ayodeji Olusegun Akinwumi, Omambala Divine; Omojola Tomiwa Yusuf "An Explainable Machine Learning Framework for Political Instability Prediction and Early Warning Using Decision Tree Learning" Iconic Research And Engineering Journals, 10(1) https://doi.org/10.64388/IREV10I1-1719457