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

References

[1] Centre for Systemic Peace, “Global Trends in Armed Civil Conflict, 1946–2015,” Centre for Systemic Peace, 2016. [Online]. Available: https://www.systemicpeace.org

[2] J. T. Bang, A. Basuchoudhary, A. David, and A. Mitra, “Predicting Terrorism: A Macro-Level TimeSeries Approach,” Defence and Peace Economics, 2016.

[3] World Bank, The Changing Wealth of Nations: Measuring Sustainable Development in the New Millennium, World Bank, 2011.

[4] Political Instability Task Force (PITF), “Worldwide Atrocities Dataset and Coding Manual,” Centre for Systemic Peace.

[5] F. Caselli and W. J. Coleman, “On the Theory of Ethnic Conflict,” Journal of the European Economic Association, vol. 11, no. s1, pp. 161–192, 2013.

[6] H. Mueller, “Growth and Violence: Argument for a Per Capita Measure of Civil War,” Economica, vol. 83, no. 331, pp. 473–497, 2016.

[7] Rishi, “What Leads to Political Instability,” B.A. Political Science & Sociology, University of Jammu, 2018. [Online]. Available: https://www.quora.com/ What-leads-to-political-instability

[8] A. Geron, ´ Hands-On Machine Learning with Scikit-Learn and TensorFlow, 1st ed. Sebastopol, CA, USA: O’Reilly Media, 2017.

[9] N. Castle, “Supervised vs. Unsupervised Machine Learning Algorithms,” DataScience.com, 2018. [Online]. Available: https://www.datascience.com/blog/ supervised-and-unsupervised-machine-learning-algorithms

[10] G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning, Springer, vol. 112, 2013.

[11] L. Breiman, “Bagging Predictors,” Machine Learning, vol. 24, no. 2, pp. 123–140, 1996.

[12] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

[13] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.

[14] Fund for Peace, “Fragile States Index Methodology (CAST Framework),” Fund for Peace, 1957– present. [Online]. Available: http://ffp.statesindex.org 9

[15] C. Perry, “Machine Learning and Conflict Prediction: A Use Case,” Stability: International Journal of Security and Development, vol. 2, no. 3, pp. 1–18, 2013.

[16] B. Huffman et al., “Predicting High-Risk Countries for Political Instability and Conflict,” Stanford University CS229 Project Report, 2015.

[17] B. Celiku et al., “Predicting Conflict,” World Bank Policy Research Working Paper, 2017.

[18] H. Mueller and C. Rauh, “Reading Between the Lines: Prediction of Political Violence Using Newspaper Text,” American Political Science Review, vol. 112, no. 2, pp. 358–375, 2018. (Originally CEPR Discussion Paper No. 11516, 2016.) [19] H. Hegre, H. Buhaug, K. Calvin, J. Nordkvelle, S. Waldhoff, and E. Gilmore, “Forecasting Civil Conflict Along the Shared Socioeconomic Pathways,” Environmental Research Letters, vol. 11, no. 5, pp. 1–8, 2016.

[19] L.-E. Cederman and N. B. Weidmann, “Predicting Armed Conflict: Time to Adjust Our Expectations?” Science, vol. 355, no. 6324, pp. 474–476, 2017.

[20] M. Colaresi and Z. Mahmood, “Do the Robot: Lessons from Machine Learning to Improve Conflict Forecasting,” Journal of Peace Research, vol. 54, no. 2, pp. 193–214, 2017.

[21] D. Muchlinski, D. Siroky, J. He, and M. Kocher, “Comparing Random Forest with Logistic Regression for Class-Imbalanced Civil War Onset Data,” Political Analysis, vol. 24, pp. 87–103, 2016.

[22] M. D. Ward, N. W. Metternich, C. L. Dorfi, M. Gallop, F. M. Hollenbach, A. Schultz, and S. Weschle, “Learning from the Past and Stepping into the Future: Toward a New Generation of Conflict Prediction,” International Studies Review, vol. 15, no. 4, pp. 473–490, 2013.

[23] J. A. Goldstone et al., “A Global Model for Forecasting Political Instability,” American Journal of Political Science, vol. 54, no. 1, pp. 190–208, 2010. [25] W. McKinney, “pandas: A Foundational Python Library for Data Analysis and Statistics,” Python for High Performance and Scientific Computing, pp. 1–9, 2011.

@article{1719457,
      author = {Olatunde David Akinrolabu, Samuel Ohirenume Afekhiku, Victor Olumide Otokiti, Ayodeji Olusegun Akinwumi, Omambala Divine; Omojola Tomiwa Yusuf},
      title = {An Explainable Machine Learning Framework for Political Instability Prediction and Early Warning Using Decision Tree Learning},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {1},
      pages = {252-260},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1719457.pdf},
      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.},
      month = {July},
      doi = {https://doi.org/10.64388/IREV10I1-1719457}
  }