KLASTERISASI TRACER STUDY ALUMNI UNIVERSITAS PEMBANGUNAN NASIONAL “VETERAN” JAWA TIMUR MENGGUNAKAN ALGORITMA K-MEANS

Fernaldy, Fabiyan Atha (2024) KLASTERISASI TRACER STUDY ALUMNI UNIVERSITAS PEMBANGUNAN NASIONAL “VETERAN” JAWA TIMUR MENGGUNAKAN ALGORITMA K-MEANS. Undergraduate thesis, Universitas Pembangunan Nasional Veteran Jawa Timur.

	Text (Cover) 20082010077_Cover.pdf Download (1MB)
	Text (Bab 1) 20082010077_Bab I.pdf Download (209kB)
	Text (Bab 2) 20082010077_Bab II.pdf Restricted to Repository staff only until 13 December 2027. Download (256kB)
	Text (Bab 3) 20082010077_Bab III.pdf Restricted to Repository staff only until 13 December 2027. Download (388kB)
	Text (Bab 4) 20082010077_Bab IV.pdf Restricted to Repository staff only until 13 December 2027. Download (2MB)
	Text (Bab 5) 20082010077_Bab V.pdf Download (203kB)
	Text (Daftar Pustaka) 20082010077_Daftar Pustaka.pdf Download (211kB)
	Text (Lampiran) 20082010077_Lampiran.pdf Restricted to Repository staff only until 13 December 2027. Download (530kB)

Abstract

This thesis aims to cluster the alumni tracer study data of Universitas Pembangunan Nasional “Veteran” East Java using K-Means algorithm. This clustering is done to group alumni based on their career characteristics, which are measured through Grade Point Average (GPA), waiting time to get a job, and the relationship between work and study program. The data used in this thesis are the results of filling out the tracer study questionnaire from 2021 to 2022, with a total of 5,313 alumni data. The methods used in this thesis include data preprocessing, normalization, and visualization using the Improved Visual Assessment for Tendency (iVAT) technique and the elbow method to determine the optimal number of clusters. The clustering results show that there are three clusters based on GPA and waiting time, and two clusters based on the relationship between work and study program and waiting time. In the study, 2 clusterizations were conducted using different dimensions, the first clusterization, namely the GPA with the waiting period for alumni to get a job, resulted in a number of 3 clusters with a Silhoutte coefficient evaluation value of 0.499046 (having a cluster structure that tends to be weak). As an output, this thesis produces a website that presents a visualization of the clustering results, so that it can be accessed and used by the university to evaluate and improve the quality of education and support alumni career development. Keywords: Clustering, Tracer Study, K-Means

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Arifiyanti, Amalia Anjani	NIDN6685718	amalia_anjani.fik@upnjatim.ac.id
Thesis advisor	Yudha Kartika, Dhian Satria	NIDN0722058601	dhian.satria@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Information Systems

Depositing User:

Fabiyan Atha Fernaldy

Date Deposited:

13 Dec 2024 07:50

Last Modified:

13 Dec 2024 07:50

URI:

https://repository.upnjatim.ac.id/id/eprint/33356