Machine Learning for Job Matching, Skills Mapping and Labour Market Forecasting in e-Government Systems

Unemployment among Tanzanian youth remains a critical socio-economic issue despite the introduction of e-Government platforms for job facilitation. However, existing systems under the Prime Minister’s Office Labour, Youth, Employment and Persons with Disability (PMO-LYED) face inefficiencies, limited accessibility, and weak data-driven decision-making. This study was motivated by the need to address the gap by exploring how advanced technologies could strengthen employment facilitation services. The main objective was to apply machine learning (ML) techniques to improve efficiency, accuracy, and accessibility of e-Government employment systems. Specifically, the study sought to identify key challenges limiting service effectiveness, analyze the impact of inefficiencies on unemployment, integrate ML models for optimized job-matching and labour-market forecasting, and provide actionable recommendations for system enhancement. A mixed-methods design was employed, integrating surveys, interviews, and document reviews with quantitative analysis of system usage data. ML models, including Random Forests, clustering algorithms, and natural language processing, were applied to assess job-matching effectiveness, system usability, and user sentiment. Findings revealed poor system usability, weak job-skill matching, and lack of real-time updates as major challenges. However, 86.7% of respondents supported ML integration, with intelligent job-matching and skills gap analysis identified as highly desired features. The study concludes that integrating ML into Tanzania’s e-Government employment platforms can substantially enhance decision-making, increase efficiency, and align job-seekers with labour-market demands. It recommends user-centered system design, infrastructure investment, targeted training, and continuous monitoring to ensure sustainability. These findings provide a roadmap for policymakers and developers to strengthen digital employment services and reduce unemployment in Tanzania.