Exploring Person-Job Fit Influence on Innovation Behavior through Machine Learning Approach in Public Sector Banking Institutions

This research explores the impact of person-job fit on innovation behavior in public sector banking institutions in India. This analysis relies on machine learning tools, such as regression and decision trees. The research is based on a sample of 388 professionals across three public sector banks. Job involvement serves as a mediating factor in the described relationship, while the moderating variable is the career commitment of the participants. According to the results of this study, the person- job fit impacted the innovation behavior. The Logistic Regression showed accuracy on average at 87.3%, precision at 89.0%, recall at 85.1%, and an F1 score at 87.0%. At the same time, it showed an average AUC-ROC of 0.92, as well as MSE at 0.13 and RMSE at 0.36. The Decision Trees showed accuracy on average at 84.7%, precision at 87.1%, recall at 82.7%, and an F1 score at 84.7%. The average AUC-ROC was 0.89; the MSE was 0.16, and RMSE was 0.40. Such findings suggest that person- job fit is a critical factor for innovation behavior among public sector bank employees. Additionally, it is evident that machine learning algorithms can be used to predict person- job fit performance, and such performance is likely to lead to innovation behavior. Furthermore, the study helps to understand the influence person- job fit has on innovation behavior through career commitment and job involvement. The findings, therefore, offer useful insights into organizational behavior in the banking sector.