Document Details

Document Type : Thesis 
Document Title :
PERFORMANCE EVALUATION OF EMPLOYEES USING DATA MINING TECHNIQUES TO SUPPORT DECISION MAKING IN HUMAN RESOURCE MANAGEMENT
تقييم أداء الموظفين باستخدام تقنيات التنقيب عن البيانات لدعم صنع القرار في إدارة الموارد البشرية
 
Subject : Faculty of Computing and Information Technology 
Document Language : Arabic 
Abstract : Performance evaluation of employees using data mining techniques to support decision making in human resource management Amani Mustafa Y. Ghazzawi Supervised By Dr. Shaimaa Salama ABSTRACT Human resources management needs to understand the factors affecting their employees’ behavior and performance to help organizations make the best decisions and utilize the benefit of their employees’ capabilities. There is a difference in the factors affecting the performance of employees depending on the regulatory environment, whether in the educational or business sectors. Data mining technology is an effective decision support tool that contributes to the analysis and evaluation of employee performance. This thesis aims to improve the performance of faculty members through identification of the factors affecting their performance and prediction of suitable decisions for new faculty members to maximize staff performance and thus achieve higher learning quality. A model based on data mining is developed for the universities sector, which contributes to understanding the factors affecting the performance of faculty members. A K-mean algorithm is applied to faculty data based on specific features of faculty members, to divide them into groups with similar characteristics. Each cluster is analyzed and a decision is recommended. The next step of the model is predicting the decision needed for newcomers depending on the decisions specified on the clustering step. Four classification algorithms (Random Forest, Naive Bayes, K-Nearest Neighbors, Decision Tree) are applied to the data and compared to identify the best resulted performance. The results showed that the random forest algorithm provides better prediction results than other algorithms with an accuracy of 97.86%. 
Supervisor : Dr. Shaimaa Salama 
Thesis Type : Master Thesis 
Publishing Year : 1441 AH
2020 AD 
Added Date : Wednesday, March 11, 2020 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
أماني مصطفى غزاويGhazzawi, Amani MustafaResearcherMaster 

Files

File NameTypeDescription
 46048.pdf pdf 

Back To Researches Page