Predictive Modeling of Candidate Personality Traits For Recruitment Using Machine Learning Techniques

Personality prediction using machine learning has become an essential area of research, particularly in fields such as recruitment, career counselling, and behavioral analysis. Traditional personality assessments, often based on self-reported questionnaires, are subject to human bias and inconsistencies. Recent developments in artificial intelligence and machine learning have led to the creation of automated models for predicting personality that evaluate a range of data types, such as text, social media behaviour, vocal tones, and facial expressions. This literature review examines current studies on personality forecasting, emphasizing various machine learning methods, sources of data, and assessment criteria. Research utilizing classification techniques like support vector machines, random forests, logistic regression, and gradient boosting has shown encouraging outcomes in forecasting personality traits derived from recognized psychological frameworks, such as the Big Five Personality Traits. Moreover, techniques in natural language processing are essential for extracting linguistic characteristics from potential responses to enhance prediction accuracy. Numerous studies have also pointed out the impact of AI in recruitment, illustrating how personality prediction models contribute to diminishing biases, refining decision-making, and optimizing job-candidate alignment. This survey provides a comparative analysis of various approaches, discusses their strengths and limitations, and identifies future research directions for developing more robust, scalable, and interpretable personality prediction systems.