Evaluation of Factors Affecting Employees' Performance Using Artificial Neural Networks Algorithm: The Case Study of Fajr Jam


  •  Mohammad Rahmanidoust    
  •  Jianguo Zheng    

Abstract

Human resources are the most valuable assets of any organization. Therefore, human resources performance has the greatest impact on the organization's performance and its ability to operate. Many factors affect the performance of employees in organizations. In this research, we seek to evaluate the factors affecting the performance of Fajr Jam refinery employees. For this purpose, firstly, the literature of the research, the indicators affecting the performance of employees were identified and the conceptual model of the problem was formed. Then, the required data were collected using a standard questionnaire based on the conceptual model of the problem among employees of FJG Company. After assessing the validity and reliability of the collected data, it is time to evaluate the performance of the indicators. For this purpose, an artificial neural network algorithm was used to estimate the efficiency boundary values. After calculating the efficiency values in the presence of all the indices, each indices were eliminated from the conceptual model and again the efficiency values were estimated. Now, by comparing the performance statistics in the state before and after the removal of each indicator from the conceptual model, the degree and the mode of its effect are determined. The results of this study indicate that the "payroll" indicators, "environmental conditions" and "reporting culture" are the strengths of the system under review, and are now at an appropriate level. Also, the results indicate a negative impact on the indicators of "awareness", "system planning and preparation for critical situations," "amenities," "training," and "job security" in the system under review.



This work is licensed under a Creative Commons Attribution 4.0 License.
  • Issn(Print): 1913-9004
  • Issn(Onlne): 1913-9012
  • Started: 2008
  • Frequency: monthly

Journal Metrics

Google-based Impact Factor (2019): 14.58

h-index (February 2019): 54

i10-index (February 2019): 453

h5-index (February 2019): 26

h5-median(February 2019): 35

( The data was calculated based on Google Scholar Citations. Click Here to Learn More. )

Contact