An Explainable AI Approach for Employee Promotion Prediction Using XGBoost and SHAP with LLM Prescriptive Career Path Optimisation

ST1135: An Explainable AI Approach For Employee Promotion Prediction Using XGBoost And SHAP With LLM Prescriptive Career Path Optimisation

Najwa Binti Mahmood Universiti Teknologi PETRONAS (UTP)

VIC26 | Tertiary (Science And Technology)

Employee promotion decisions are critical in Human Resource Management (HRM), yet traditional evaluation methods often rely on subjective judgement that may lead to bias and inconsistency. This project introduces an AI-driven promotion decision support platform using employee performance, competency and certification data from a Malaysian company to deliver fairer and more transparent assessments. By integrating Explainable Artificial Intelligence (XAI), SHAP and Large Language Models (LLMs), the system provides understandable prediction explanations and personalised career development recommendations through an interactive Streamlit dashboard. The solution achieved over 97% predictive accuracy, empowering organisations to modernise progression through smarter, bias-aware and future-ready workforce management.

Virtual Booth

ST1135: An Explainable AI Approach For Employee Promotion Prediction Using XGBoost And SHAP With LLM Prescriptive Career Path Optimisation

VIC26 | Tertiary (Science And Technology)