Salary Prediction Model for Non-academic Staff Using Polynomial Regression Technique

Abstract

The idea of regression has increased rapidly and significantly in the machine learning domain. This paper builds a salary prediction model to predict a justifiable salary of an employee commensurate to the increase or decrease in exchange rate (XR) using polynomial regression (PR) techniques of degree 2 in Jupyter Notebook on Anaconda Navigator tool. Predicting a feasible salary for an employee by the employer is a challenging task since every employee has a high goal and hope as the standard of leaving increases without a corresponding increase in salary. This model uses a salary dataset from Taraba State University, Jalingo, Nigeria in building and training the model and XR dataset for the prediction of employee salary. The result of the research shows that since the distribution of the dataset was nonlinear and the major feature significant in determining employee’s salary from the in-salary dataset was grade level and XR, this fully confirmed the use of PR algorithm. The research has immensely contributed to the knowledge and understanding of regression techniques. The researcher recommended other machine learning algorithms explored with various salary datasets and the potential applicability of machine learning fully incorporated in the financial department on the large dataset for better performance. The model performance was evaluated using R2 scores accuracy and the value of 97.2% realized, indicating how well the data points fit the line of regression and unseen dataset in the developed model.

Received: 24 February 2023 | Revised: 10 May 2023 | Accepted: 26 May 2023

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The average XR data that support the findings of this study are openly available at www.cbn.gov.ng/rates/exrate.asp.

Author Contribution Statement

Samuel Iorhemen Ayua: Conceptualization, Methodology, Software, Formal analysis, Data curation, Visualization, Project administration. Yusuf Musa Malgwi: Investigation, Resources, Data curation, Writing - original draft, Writing - review & editing, Supervision, Project administration. James Afrifa: Validation, Resources, Visualization.