| Abstrakt: |
The delayed existing assessment practices in organizations created a setback for the progress of the advanced employees into their new jobs. In this manner, to avoid delay, the given paper proposes a predictive framework in the context of human resource (HR) analytics with the assistance of agile methodology and machine learning (ML) classifiers. The proposed structure is utilized with agile methodology to recognize a couple of variables that could be properties in the predictive system for concluding which employee will get promoted in view of their past experiences. This methodology involves phases such as requirements planning, design, development, testing, and deployment. It covers the end-to-end pipeline in a machine learning framework, which includes the pre-processing of data, feature selection, classification, and validation. The performance of the proposed framework is validated based on metrics such as accuracy, sensitivity, and specificity by taking an open-source Kaggle dataset (‘Employee’s performance for HR analytics’) into consideration. The results show that the proposed framework efficiently outperforms the recent techniques, thereby contributing to the productivity, collaboration, and well-being of employees in an organization. |
Full text from SpringerLink