MARATTO

article

Towards a new method for classifying employee performance using machine learning algorithms

Abstract

Nowadays, the human factor is becoming more decisive in achieving the overall performance of companies and subsequently in improving their competitiveness and their productivity, which makes Human Resources (HR) practices, in particular the performance management, a strategic function of companies.However, the mass of data generated by the HR Information System (HRIS) continues to multiply. Moreover, new external information resources are now available, such as social networks or measurements from physical devices, which constitute a profound digital transformation of HR data and its management. Thus, traditional Information Technology (IT) tools are no longer able to keep up with this growth of HR data in terms of volume, variety, veracity, velocity, and added Value, companies are not able to understand past phenomena such as the causes of non-performance of employees or to anticipate the departure risk of their key skills. Therefore, a big data project is no longer an option, it becomes unavoidable to stay in the race for competitiveness, productivity, and profitability [1].In this study, we establish a model to predict employee’s performance using machine learning algorithms in particular Principal Component Analysis (PCA) for dimensionality reduction and multinomial logistic regression (MLR) for classification. The result of this work represents a decision support model for managers to develop a tailor-made team around the overall strategy of the company, to set up an action plan to anticipate the departure of high performers.

Research topics

  • AI and HR Technologies
  • Customer churn and segmentation
  • Big Data and Business Intelligence

Sustainable Development Goals

Read the original research

This page summarises published work. The authoritative version sits with the publisher.

DOI: 10.1109/iscv54655.2022.9806118

Is something wrong with this record? Report it or request removal.

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.