A Task Performance and Fitness Predictive Model Based on Neuro-Fuzzy Modeling
Femi Johnson, Adebukola Onashoga, Oluwafolake Esther Ojo, Adejimi Alaba, Opakunle Victor · Artificial Intelligence and Applications · 2023
Recruiters' decisions in the selection of candidates for specific job roles are not only dependent on physical attributes and academic qualifications but also on the fitness of candidates for the specified tasks. In this paper, we propose and develop a simple neuro-fuzzy-based task performance and fitness model for the selection of candidates. This is accomplished by obtaining from Kaggle (an online database) samples of task performance-related data of employees in various firms. Data were preprocessed and divided into 60%, 20%, and 20% for training, validating, and testing the developed neuro-fuzzy-based task performance model respectively. The most significant factors influencing the performance and fitness rating of workers were selected from the database using the Principal Components Analysis (PCA) ranking technique. The effectiveness of the proposed model was assessed, and discovered to generate an accuracy of 0.997%, 0.08% Root Mean Square Error (RMSE), and 0.042% Mean Absolute Error (MAE). Received: 25 April 2023 | Revised: 13 July 2023 | Accepted: 27 July 2023 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in Kaggle dataset, Employee Attrition and Factors at https://www.kaggle.com/datasets/thedevastator/employee-attrition- and-factors.