AI-Driven Talent Acquisition: Predicting Employee Success in Indian Public Sector Recruitment

Indian public sector talent acquisition encounters obstacles from manual examination processes, resulting in inefficient procedures that create biased decisions that reduce the accuracy of candidate selection. A proposed framework uses AI with ML, DL, and NLP to forecast hiring success by analyzing recruitment datasets from Indian government websites. The model’s name should be clear, as well as its objective, the AI methods (ML, DL, and NLP, the main metrics 92.3% F1-score) and what benefits it brings to real-world problems, like hirings. Give the results in numbers bias went down 23.7% and time saved was nearly 40% and outline what this approach offers to the Indian public sector. The experimental data demonstrates that the new hiring process using AI achieved a hiring accuracy rise of 21.4% together with a time reduction of 39% and a bias reduction of 23.7% beyond standard hiring systems. The model delivered a 92.3% F1-score exceeding the F1-scores achieved by currently used AI solutions for hiring. The proposed recruitment system boosts processing efficiency and higher fairness and transparency while providing excellent suitability for large government hiring programs. In the Future, it will concentrate on implementing the model in real-time applications together with developing its capabilities to adapt to multiple positions across different job categories.