This study by In-Sue Oh and colleagues, published in the Journal of Applied Psychology, uses interpretable machine learning to explore the relationship between five-factor model (FFM) personality traits and job performance. Nonlinear ML models slightly outperform traditional linear methods, particularly when using detailed personality facets. Conscientiousness is the strongest predictor, showing a curvilinear effect where extremely high levels do not further increase performance. Agreeableness also shows a slight nonlinear relation. Specific personality facets vary in importance depending on job type, with some facets of agreeableness and extraversion significant for different sales roles. These findings suggest ML can better capture complex personality-performance relations, enhancing personnel selection and development.
Revisiting the Nature and Strength of the Personality Job Performance Relations: New Insights from Interpretable Machine Learning
