Abstract
Performance prediction of students in university courses is a crucial concern to all higher education institutions managements where several factors may affect their students’ performance. In Computer Science related programs, programming courses and having the skills of algorithm analysis are made compulsory subjects in most institutions of learning. Having mathematical skills play a vital role to be a good programmer and algorithm analysis. In this study an attempt was made to build a model which predict the performance of students in the Algorithm Analysis based on their grades of other courses, specifically by evaluating preliminary programming courses and different mathematics courses of the curricula. The data was collected from Wolkite University, Computing and Informatics College of Computer Science under graduate students of 2015-2018 batch students. To build the model classification algorithms, namely, Decision tree, Naïve Bayes and Support Vector Machine (SMO) were applied using Weka machine learning tool. The experiment from the study shows that a priori knowledge of the Data structure and Algorithm and Fundamentals of Programming I are essential to excel in the course Algorithm Analysis for computer science students. This work will be of considerable importance in identifying students who has low performance on this courses and the students will be advised to take action on their skill gap in timely manner. Finally, the classification algorithms were tested and performances comparison were made. The decision tree (J48) algorithm provides a promising result of 78.313%.
Keywords:
Data Mining, Classification, Decision tree, Data Structure and Algorithm, Performance, K-Fold Cross Validation
References
• D. David L. Olson and Dursun, “Advanced Data Mining Techniques, Springer-Verlag: Berlin Heidelberg”, 2008.
• Jing Luan (2006). Data Mining Applications in Higher Education, SPSS,www.spss.com/ Downloaded in July 2020.
• Pratiyush Guleria, Manu Sood, “Big Data Anlalytics: Predicting Academic Course Preference Using Hadoop Inspired MapReduce”, IEEE, 2017.
• Y. K. Saheed, T. O. Oladele, A. O. Akanni and W. M. Ibrahim. “STUDENT PERFORMANCE PREDICTION BASED ON DATA MINING CLASSIFICATION TECHNIQUES” 2018.
• Anoopkumar M, A. M. J. Md. Zubair Rahman,” Model of Tuned J48 Classification and Analysis of Performance Prediction in Educational Data Mining”, 2018.
• Lakshmipriya. K, Dr. Arunesh P.K, “PREDICTING STUDENT PERFORMANCE USING DATA MINING CLASSIFICATION TECHNIQUES”, 2017.
• Mashael A. Al-Barrak and Muna Al-Razgan,”Predicting Students Final GPA Using Decision Trees: A Case Study”, 2016.
• Ghada Badr, Afnan Algobail, Hanadi Almutairi, Manal Almutery.” Predicting Students’ Performance in University Courses: A Case Study and Tool in KSU Mathematics Department”, 2016.
• Fiseha Berhanu, Addisalem Abera, “Students’ Performance Prediction based on their Academic Record”, 2015.
• Raheela Asif, “Predicting Student Academic Performance at Degree Level: A Case Study”, 2015.
• Parneet Kaur, Manpreet Singh, Gurpreet Singh Josan,” Classification and prediction based data mining algorithms to predict slow learners in education sector”, 2015.
• V.Ramesh, P.Parkavi. K.Ramar, “Predicting Student Performance: A Statistical and Data Mining Approach”, 2013.
• Surjeet Kumar Yadav, Saurabh Pal,”Data Mining: A Prediction for Performance Improvement of Engineering Students using Classification”, 2012.
• O.S. Akinola, B.O. Akinkunmi, T.S. Alo, “A Data Mining Model for Predicting Computer Programming Proficiency of Computer Science Undergraduate Students”, 2012.
• N. M. Norwawi, S. F. Abdusalam, C. F. Hibadullah, B. M. Shuaibu “Classification of Students’ Performance in Computer Programming Course According to Learning Style”, 2009.
• Qasem A. Al-Radaideh, Emad M. Al-Shawakfa, and Mustafa I. Al-Najjar, “Mining Student Data Using Decision Trees”, 2006.
Downloads
Download data is not yet available.
