Open AccessEvaluating the Performance of Engineering’s Students in Mathematic Subject based on Academic Decision-Making Techniques
Author(s) -
Abbas Atwan Mhawes,
Ahmed Yousif Falih Saedi,
Ali Talib Qasim al-Aqbi,
Lamees abdalhasan Salman
Publication year - 2021
Publication title -
webology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.259
H-Index - 18
ISSN - 1735-188X
DOI - 10.14704/web/v18i2/web18313
Subject(s) - c4.5 algorithm , computer science , cluster analysis , data mining , machine learning , artificial intelligence , identification (biology) , naive bayes classifier , data science , botany , support vector machine , biology
Data mining is characterized as a quest for useful knowledge via large quantities of data. Some basic and most common techniques for data extraction are association rules, grouping, clustering, estimation, sequence modeling. For a wide range of applications, data mining techniques are used. Techniques of data analysis are essential to the preparation and implementation of the administration of the learning system, including behavioral guidance and personal behavior appraisal. The article applies data analytical methods to the role of student classification. Several tests are used for the interpretation of the findings. In keeping with the methodology proposed in the paper, the classification using cognitive skills provides more detailed results than the findings of other study published. Five algorithms were used (J48, Naïve Bayes, Multilayer Perception, K Star and SMO). This essay discusses and measures the application of the various algorithms so that factors affecting the success and failure of students can be identified, student performance can be estimated, and the significant consequences of the mathematics system for the second university year can be identified. However the number of exams can be minimized using data mining techniques. In terms of time and consequences, this shortened analysis plays a key role.