International Journal of the Computer, the Internet and Management Vol.23 No.3 (September-December, 2015) pp. 70-74 70 Hybrid Genetic Algorithms Feature Selection and Decision Trees Classifier for Student’s Computer Self-Efficacy Wanphen Wirojcharoenwong 1 , Montean Rattanasiriwongwut 2 , and Monchai Tiantong 3 King Mongkut's University of Technology North Bangkok, Thailand 1 wi.wanphen@gmail.com 2 montean@it.kmutnb.ac.th, www.it.kmutnb.ac.th 3 monchai@kmutnb.ac.th, www.kmutnb.ac.th Abstract - Data mining techniques such as Decision Tree have been applied to the field of retail sale, e-commerce, banking etc. Data mining, the extraction of hidden relationship information from large dataset, is a powerful new technology with great potential to help business focus on the most important information in their data warehouses. Data mining techniques can learn normal and anomalous patterns from training data. Genetic algorithm can help selecting appropriate features and building optimum decision trees. In this paper, we propose a new hybrid mining approach in the design of an effective and appropriate to analyze student’s computer self-efficacy model. The new proposed hybrid classification model is established base on a combination of genetic algorithm feature selection and decision tree (C4.5) result analysis using WEKA tool. The results show that a new hybrid classification model has even higher accuracy and lower complexity. The number of leaves and size of the constructed decision tree (i.e. complexity) are less, compared with decision tree models. Keywords - Genetic Algorithms, Computer Self-Efficacy, Data Mining, Feature Selection, Decision Trees I. INTRODUCTION The increased use of Computer and Internet technology is the main tool in education activities of students because students gather more information from internet and using digital library. Therefore, perceived computer self-efficacy among teachers and students play an import part in applying computer supported education and achieving its goal [4]. The paper is organized as follows: Section 2 cover a detailed confabulation on the related works done so far. Section 3 introduce the proposed Computer Self-efficacy, Decision Tree C4.5 and Genetic Algorithm Feature Selection techniques in construction of Decision Tree models for Student’s Computer Self-Efficacy. Section 4 presents the experiment result and analysis from using the proposed method. Conclusion are discussed in Section 5. II. RELATED WORK In this section, we shall review the literature of Genetic Algorithm feature selection and Computer self-efficacy. A. Genetic Algorithm Min Chen and Ludwig, S.A. (2013) propose Fuzzy Decision Tree (FDT) classifier that is based on soft discretization by identifying the best “cut -point and applying a feature selection method that is based on the ideas of mutual information and genetic algorithms. The results show that FDT classifier obtains