Discovering Performance Evaluation Features of faculty Members using Data Mining Techniques to Support Decision Making

Human resources in organizations need to understand their employees and know the factors that influence their performance and behavior to help them in decision-making. Factors affecting employee performance may differ depending on the environment, whether in business or educational sector. The use of data mining technology is an effective tool in analyzing the characteristics of staff and evaluating them to support decision-making. This paper proposes a model based on data mining in educational sector to understand the factors that affect faculty members performance. Based on selected attributes, K-means algorithm is applied to group faculty members into clusters with similar characteristics and the appropriate decision is specified for each cluster. Based on the resulted decisions for each cluster, a classification algorithm is applied to predict the decision needs to be taken for coming staff.