Abstract
Machine learning (ML) offers powerful capabilities for large-scale data processing, predictive modelling, and decision support in complex legal and economic systems. This study investigates the application of ML techniques in judicial and economic governance, focusing on their role in optimizing institutional performance, improving case-flow management, and strengthening judicial predictability. Using judicial case data from Kazakhstan (2014–2024), during which investigative and security services nearly quadrupled, supervised and unsupervised learning algorithms are employed to model caseload dynamics, forecast procedural duration, and assess efficiency-enhancing scenarios. The results indicate that ML-based interventions can reduce case processing time by 5%–15% and increase judicial throughput by 5%–18%, significantly improving predictive accuracy, resource allocation, and operational planning. These findings highlight the potential of ML to enhance institutional efficiency, reduce procedural uncertainty, and support sustainable judicial modernisation.Copyright© 2026 The Author(s). This article is distributed under the terms of the license CC-BY 4.0., which permits any further distribution in any medium, provided the original work is properly cited.Article’s History: Received 30th of December, 2025; Revised 31st of January, 2025; Accepted 2nd of March, 2025; Available online: 30th of March, 2026. Published as article in the Volume XXI, Spring, Issue 2(92), March, 2026.