Classification model for graduation on time study using data mining techniques with SVM algorithm

Every college must have academic data. This academic data includes student data, course data, study plan data, achievement index, graduation data, and study period. Study period and percentage of students graduating on time become one of the important indicators in the assessment component of study...

Full description

Saved in:
Bibliographic Details
Main Authors: Zulfa, Mulki Indana, Fadli, Ari, Ramadhani, Yogi
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Artificial intelligence
Classification
Data mining
Students
Support vector machines
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Every college must have academic data. This academic data includes student data, course data, study plan data, achievement index, graduation data, and study period. Study period and percentage of students graduating on time become one of the important indicators in the assessment component of study program accreditation by BAN PT. The minimum number of students graduating on time is due to the unattended study period of students by study programs. The concept of data mining can be implemented to gain knowledge from these academic data. Data mining is a process that uses statistical, mathematical, and artificial intelligence techniques to extract useful knowledge (information) from a large database. This knowledge will be difficult to know if only using manual processes without using data mining technology. One technique used by data mining is the SVM algorithm. The SVM algorithm will build a classification model and determine which variable has the most influence on graduation on time. As a result, the semester achievement index becomes the main factor determining whether students will graduate on time or not.
ISSN:0094-243X
1551-7616
DOI:10.1063/1.5097475