Comparative Analysis on Dimension Reduction Algorithm of Principal Component Analysis and Singular Value Decomposition for Clustering

Abstract

Clustering is a method of dividing datasets into several groups that have similarity or the same characteristics. High-dimensional Datasets will influence the effectiveness of the grouping process. This study compares two dimension reduction algorithms, namely Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) using K-Means clustering method to find out the best algorithm with the smallest Bouldin Davies Index evaluation. The dataset of this study involved public data from UCIMachine Learning which contains the number of weekly sales of a product. Data processing is performed by comparing the number of clusters from 3 to 10 and the dimension reduction from 2 to 10. From the data processing the RapidMiner tools, application with dimension reduction can provide better results than without dimension reduction. In particular, the PCA algorithm shows better results than the SVD, with which the best number of clusters is 5, and the number of dimensional reductions is 3 with a Bouldin Index of 0.376.

Pengelompokan Data Nilai Siswa Menggunakan Metode K-Means Clustering

“…K-Means clustering merupakan sebuah algoritma unsupervised learning yang digunakan dalam pengelompokan data dalam dataset yang tidak memiliki label kedalam sebuah cluster-cluster yang berbeda [7]- [9]. K-Means clustering memungkinkan pengguna melakukan pengelompokan data kedalam cluster berdasarkan variabel-variabel yang ada tanpa harus melalui proses training data terlebih dahulu.…”

Comparison of K-Means & K-Means++ Clustering Models using Singular Value Decomposition (SVD) in Menu Engineering

“…The data have a minimum value of -8,724 and a maximum of 3,437. Matrix decomposition [28] and the transformation of new features generated from original data [21], [29], [30] require the Singular Value Decomposition (SVD) method. This method has a good mechanism for producing similar value characteristics [21] and can improve the performance and normalization of the same information value [29].…”

“…In this study, the evaluation of the clustering model was carried out using the Davies-Bouldin Index (DBI). DBI is a method of evaluating cluster performance by looking at the maximum distance between clusters and, at the same time, minimizing the distance between members in the cluster [30], [39]. The main idea in the evaluation of DBI is that the smaller the DBI number, the more optimal the results of the cluster formed [30], [34], [40].…”