Analisis Perbandingan Kinerja Clustering Data Mining Untuk Normalisasi Dataset

 (*)Siti Emalia Saqila Mail (Universitas Nasional, Jakarta, Indonesia)
 Intan Putri Ferina (Universitas Nasional, Jakarta, Indonesia)
 Agus Iskandar (Universitas Nasional, Jakarta, Indonesia)

(*) Corresponding Author

Submitted: October 19, 2023; Published: December 26, 2023

Abstract

Nowadays, the development and influence of technology in human life is very important, where the role of technology greatly influences the activities carried out by humans. In a company organization, technology is not only used as a process to speed up the processes carried out. The use of such important technology also increases the size or volume of available data information. A dataset is a collection of data obtained in a data warehouse. Data mining is a technique that is part of Knowledge Discovery in Database (KDD). Clustering is a grouping process carried out in data mining. The first problem that is central to the research is that the values obtained from the clustering process are sometimes still not considered optimal. The performance results of the data mining clustering algorithm cannot yet be fully used as a basis for decision making. Comparisons made in clustering data mining are used to assist in the decision making process. In this research, the algorithms that will be used for comparison of performance are the K-Means and K-Medoids algorithms. Another problem that needs special attention is the problem of data quality. The results obtained from the data mining process can be seen from the quality of the data stored or used in the data processing process. Normalization is part of preprocessing data mining which aims to re-reason it based on a new scale. Z-Score is a normalization carried out on data based on statistical functions. The results obtained in the research The role of normalization in the research is very important, this is because using Z-Score normalization can improve the performance of the K-Means and K-Medoids algorithms, this can be seen from the DBI value obtained which is smaller when normalization is carried out compared to before it is carried out normalization, which indicates that performance is better after normalization. In the comparison of algorithms, the K-Medoids algorithm gets better performance, this can be seen from the DBI value obtained at 0.773 at K=9 after normalization. Meanwhile, the K-Means algorithm obtained a value of 0.783 at K=9 after normalization as well

Keywords


Performance Comparison; Clustering; Data Mining; Normalization; Z-Score

Full Text:

PDF


Article Metrics

Abstract view : 133 times
PDF - 32 times

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Analisis Perbandingan Kinerja Clustering Data Mining Untuk Normalisasi Dataset

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Swanto Gunawan Situmorang

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Jurnal Sistem Komputer dan Informatika (JSON)
Dikelola oleh STMIK Budi Darma
Sekretariat : Jln. Sisingamangaraja No. 338 Telp 061-7875998
email : jurnal.json@gmail.com


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.