APPLICATION OF DATA MINING FOR PREDICTING SUCCESS IN LEARNING
Keywords:
success in the study, decision trees, logistic regression, data miningAbstract
The work deals with creating of model to predict the performance of students during the study using data mining, and analysis of factors affecting the achieved level of performance. The model which is created on the bases of socio-demographic data on students, and data on their behavior and attitudes towards learning and teaching process organization as a whole, seeks to classify students in one of two categories of performance. Performance is measured by students average grade achieved in the period of study. We tested two methods of data mining as follows: logistic regression and decision trees. We considered that the presented model would be served as a test for creation of broader base of updated data by usage some of the information tools, and that on the basis of this model will be defined a number of attributes that would relatively reliable predict the study preformance
Downloads
References
[1] Apte C, Weiss S., Data Mining with Decision Trees and Decision Rules. Future Generation Computer Systems, Vol. 13, 1997., str.197-210.
[2] Dunham, M., Data Mining - Introductory and Advanced Topics, Prentice Hall, 2003.
[3] Glasser, W. Control Theory.,Harper and Row. New York, 1984.
[4] Gojkov, G., Dokimologija, Beograd: Uciteljski fakultet, 1997.
[5] Masters, T., Advanced Algorithms for Neural Networks, A C++ Sourcebook, John Wiley & Sons, 1995.
[6] Naik, B., Ragothaman, S., Using Neural Networks to Predict MBA Student Success, College Student Journal, Vol. 38, No. 1, 2004, str.143-150.
[7] Kirckby, R., WEKA Explorer User Guide for Version 3-3-4, University of Waikato 2002.
[8] Zaidah, I., Daliela, R., Predicting students’ academic performance, comparing artificial neural network, decision tree and linear regression, 21st Annual SAS Malaysia Forum, 5th September 2007, Kuala Lumpur, str. 1 – 6.
[9] Witten I.H., Frank E., Data Mining: Practical Machine Learning Tools and Techniques with Java Implementation, Morgan Kaufman Publishers: San Francisco, 2000.
[10] Hardgrave, B.C., Wilson, R.L., Kent, K.A. Predicting Graduate Student Success: A Comparison of Neural Networks and Traditional Techniques, Computers & Operations Research, 21, 1994., str. 249 – 263.
[11] Han, J., Kamber, M., Data Mining – Concepts and Techniques, Morgan Kaufman Press 2001.
[12] Oladokun, V.O., Adebanjo, A. T., Charles-Owaba, O. E., Predicting Students’ Academic Performance using Artificial Neural Network, A Case Study of an Engineering Course, The Pacific Journal of Science and Technology, Vol. 9. No. 1., 2008, str. 72 –- 79.
[13] Rodić, N. (2000): Latentna struktura uspešnosti diplomiranih studenata Učiteljskog fakulteta u Somboru, Sombor: Norma, VI; 3: 25-44; Beograd: Nastava i vaspitanje, L, 1: 98 – 113.
[14] Shulruf, B., Hattie, J., Tumen, S., The Predictability of Enrolment and First-Year University Results from Secondary School Performance, The New Zealand National Certificate of Educational Achievement, Studies in Higher Education, Vol. 33, No. 6, 2008., str. 685 – 698,
[15] Симеуновић, В. (2005) Информатика, Методологија , Статистика, Висока школа унутрашњих послова, Бања Лука
[16] Sulaiman, A., Mohezar, S., Student Success Factors, Identifying Key Predictors, Journal of Education for Business, Vol. 81, No.6, 2006., str. 328 – 333.
[17] Suzić, N., PEDAGOGIJA ZA XXI VIJEK TT centar, Banja Luka, 2005.
[18] Šipka, P., Zbirka radova sa područja kriterijuma, Beograd: Odeljenje za psihologiju Vojnomedicinske akademije,1981
