A Machine Learning Approach to Predicting Digital Leadership Success in Indonesian Police Officers

We develop a predictive model to enhance digital leadership among Indonesian National Police (Polri) officers, addressing the pressing need for technological proficiency in modern law enforcement. Digital leadership, vital for combating cyber threats and improving operational efficiency, remains underdeveloped in Polri due to limited technological skills and a lack of systematic leadership identification. We train machine learning models on 564 anonymized officer records, incorporating attributes like rank, position, and education, guided by Transformational, Adaptive, and Contingency Leadership theories. The Light GBM model excels, achieving an F1 Score of 0.9674, a Log Loss of 0.2244, a Cohen's Kappa of 0.9616, and a Matthews Correlation Coefficient of 0.9620, demonstrating high predictive accuracy. This model empowers Polri to identify officers with strong digital leadership potential, enabling targeted training programs and strategic personnel selection to drive digital transformation. We prioritize ethical deployment by excluding sensitive attributes, such as religion and gender, to mitigate bias and employ k-anonymity to safeguard data privacy. Fairness audits and interpretable outputs ensure equitable and transparent decision-making. Our approach aligns with global policing trends, offering a scalable solution to enhance leadership in tech-driven environments. By integrating robust technical performance with ethical safeguards, this study contributes to Polri’s strategic goals and sets a foundation for future research in diverse policing contexts. We advocate for continuous model monitoring to sustain fairness and effectiveness in real-world applications.