Abstract. In the era of rapid automation, artificial intelligence, and digital transformation, many traditional job roles are increasingly at risk of becoming obsolete. Conventional workforce analysis methods rely heavily on static reports, manual surveys, and historical employment data, which often lack adaptability and fail to deliver quantitative risk assessments or personalized career insights. Addressing these limitations, here we proposes an AI-Based Job Obsolescence Prediction System that leverages machine learning techniques to estimate the likelihood of employment decline using structured predictive indicators. The system incorporates key factors such as automation risk, skill relevance, AI adoption level, digital skill gap, and employment growth rate to compute a continuous risk index. This index is further transformed into a probability score using a sigmoid function, enabling a more interpretable and scalable risk evaluation. To improve prediction accuracy, supervised learning algorithms such as Random Forest and XGBoost classifiers are employed, classifying job roles into High, Medium, or Low risk categories. The final output includes detailed insights such as Job Role, Risk Score, Risk Level, Predicted Timeline, and Career Upskilling Recommendations. These results are presented through an interactive Streamlit web application, ensuring user-friendly access and visualization. Developed using Python and libraries such as Pandas, NumPy, Scikit-learn, and XGBoost, the system provides a robust, scalable, and data-driven solution for workforce analytics and proactive career planning in the evolving job market.
Anilkumar et al. (2026) studied this question.