A comparative analysis of four classification algorithms for university students performance detection

Dipta, Das and Asif Khan, Shakir and Sah Golam, Rabbani and Mostafijur, Rahman and Syamimi Mardiah, Shaharum and Sabira, Khatun and Norasyikin, Fadilah and Khandker, M. Qaiduzzaman and Md. Shariful, Islam and Md. Shohel, Arman (2019) A comparative analysis of four classification algorithms for university students performance detection. In: 5th International Conference on Electrical, Control and Computer Engineering (INECCE 2019), 29-30 July 2019 , Swiss Garden Kuantan. pp. 1-12.. (Unpublished)

[img] Pdf
29. A comparative analysis of four classification algorithms.pdf
Restricted to Repository staff only

Download (152kB) | Request a copy
29.1 A comparative analysis of four classification algorithms.pdf

Download (91kB) | Preview


The student's performance plays an important role in producing the best quality graduate who will responsible for the country's economic growth and social de-velopment. Labor market also concern with student's performance because the fresh graduate students are considered as an employee depends on their academic performance. So, identification the reason behind student’s performance variation provides a valuable information for planning education and policies. Many researchers try to find out the reason with different types of data mining approaches in different countries. But none of them worked with Bangladeshi students. This paper proposed a model for identifying the key factors of variation Bangladeshi students’ academic performance and predicts their results. This paper proposes a model which able to identify the students who need special attention. Different types of feature selection methods were used such as Co-relation, Chi-Square and Euclidean distance to select valuable features. And showing the comparison of feature selections result through decision tree, Naive Bayes, K-nearest neighbor and Artificial Neural Network classifiers algorithm. The performance analysis is done by using student SGPA and review on given facilities from a university. From the performance analysis result it is found that, decreasing number of classes in dataset, the Artificial Neural Network(ANN) (93.70%) performs better than Decision Tree(DT)(92.18%), K-Nearest Neighbors (KNN)(77.74%) and Naïve Bayes (NB)(68.33%). However, increasing number of classes in dataset the DT perform better then ANN, KNN, NB.

Item Type: Conference or Workshop Item (Lecture)
Uncontrolled Keywords: Educational data mining(EDM); Academic Performance(AP); Feature Selection(FS); Cumulative Grade Point Average(CGPA); Semester Grade Point Average(SGPA)
Subjects: T Technology > TJ Mechanical engineering and machinery
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: Faculty of Electrical & Electronic Engineering
Depositing User: Pn. Hazlinda Abd Rahman
Date Deposited: 17 Dec 2019 03:34
Last Modified: 17 Dec 2019 03:34
URI: http://umpir.ump.edu.my/id/eprint/25983
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item