KMAN Publication Inc. (KMANPUB) International Journal of Innovation Management and Organizational Behavior (IJIMOB) 3041-8992 6 Serial Number 27 2026 07 01 Random Forest Prediction of Employee Turnover Intention Using Organizational, Psychological, and Job-Related Variables Random Forest Prediction of Employee Turnover Intention Using Organizational, Psychological, and Job-Related Variables 1 18 EN Journal Article 2026 04 21 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> This study aimed to develop and evaluate a Random Forest model for predicting employee turnover intention using organizational, psychological, and job-related variables among employees in Canada.</p> <p><strong>Methods and Materials:</strong> This quantitative, cross-sectional predictive study was conducted among 428 employees working in public and private organizations across Canada. Participants were recruited from diverse occupational sectors and completed measures of perceived organizational support, organizational commitment, organizational justice, supervisor support, career development opportunities, perceived stress, psychological well-being, work engagement, burnout, occupational self-efficacy, job satisfaction, workload, job autonomy, role clarity, job insecurity, work–life balance, compensation adequacy, and turnover intention. The dataset was stratified into training and independent test subsets using an 80:20 ratio. A Random Forest classifier was optimized through stratified five-fold cross-validation. Predictive performance was assessed using accuracy, precision, sensitivity, specificity, F1 score, and receiver operating characteristic area under the curve. Permutation importance and SHapley Additive exPlanations were used to interpret predictor contributions.</p> <p><strong>Findings:</strong> Turnover intention was significantly associated with all examined predictors. The strongest correlations were observed for job satisfaction (r = -.62, p &lt; .001), organizational commitment (r = -.58, p &lt; .001), burnout (r = .55, p &lt; .001), perceived organizational support (r = -.51, p &lt; .001), and job insecurity (r = .49, p &lt; .001). In the independent test sample, the optimized Random Forest model achieved an accuracy of .86, precision of .83, sensitivity of .82, specificity of .89, F1 score of .82, and ROC-AUC of .92. Feature-importance analyses identified job satisfaction, organizational commitment, burnout, perceived organizational support, and job insecurity as the most influential predictors.</p> <p><strong>Conclusion:</strong> Employee turnover intention can be predicted with high discriminatory accuracy by integrating organizational, psychological, and job-related variables, with job satisfaction, commitment, burnout, organizational support, and job insecurity representing particularly important indicators of turnover risk.</p> </td> </tr> </tbody> </table> https://www.journals.kmanpub.com/index.php/ijimob/article/download/5674/11841