An Analysis of Urban and Rural Students Programming Skills Performance Using Clustering Techniques

37 Abstract— Educational Data mining is a recent trend where data mining methods are experimented for the improvement of student performance in academics. The work describes the mining of higher education urban and rural students’ related attributes such as improvement, behavior, attitude and relationship. The data were collected from Dr.Ambedkar Government Arts College in terms of the mentioned attributes. The proposed work explored improvement Behavior Attitude Relationship Clustering (IBARC) Algorithm, which showed the improvement in students’ performance in terms of Improvement predicting good behavior, average attitude and good relationship with faculty members and Tutors. The Hierarchical clusters were grouped with related similarities and analysis was experimented using WEKA tool. The resulted analysis describes the input parameters were found optimal. These systems do not permit the closely monitoring of students’ academic activities, the evaluation of their academic success and the support of academic activities concerning with teaching and tutoring. This dissertation makes use of cluster analysis to segment students into groups according to their characteristics and also will help the teachers to reduce the drop out ratio to a significant level and improve the performance of students. It also focuses on feedback analysis of teachers by students. Clustering is one of the basic techniques often used in analyzing data sets. The main goal of clustering is to partition students into homogeneous groups according to their characteristics and abilities. These applications can help both instructor and student to enhance the quality education. Improving students’ academic performance is not an easy task for the academic community of higher learning.