Comparison of Single Linkage, Complete Linkage, and Average Linkage Methods on Community Welfare Analysis in Cities and Regencies in East Java

Abstract

Community welfare is one of the important points for a region and is also the essence of national development. The welfare of the people in Indonesia is fairly unequal, especially in East Java. To be able to map an area to the welfare of its people in East Java, one way that can be used is to use clustering. The hierarchical clustering method is one of the clustering methods for grouping data. In hierarchical clustering, single linkage, complete linkage, and average linkage methods are suitable methods for grouping data, which will compare the best method to use. The results of the calculation show that the average linkage method with three clusters is the best calculation with a silhouette index value of 0.6054, with the 1st cluster there are 23 regions, namely the city/district with the highest community welfare, the 2nd cluster there are 11 regions, namely cities/districts with moderate social welfare, and in the third cluster there are 4 regions, namely cities/districts with the lowest community welfare.

Analysis of Regional Potential in Merauke Regency Based on Superior Livestock Population Using a Hybrid Algorithm

“…A good silhouette index value is close to 1 [45]. Research related to the comparison of clustering using the hierarchical algorithm Single Linkage, Complete Linkage, and Average Linkage Methods on Community Welfare shows that the best results for the silhouette index test use the average linkage method with 3 clusters with a value of 0.6054 compared to other methods [46].…”

Evaluation of Distance Measurement Using Complete Linkage Method

“…Akmal Fikri, et al have conducted research entitled Comparison of K-Means Clustering and Complete Linkage in Grouping Financial Technology Loan Distribution showing that the K-Means method is able to form an optimal number of clusters better than Complete Linkage based on the DBI value [8]. Yanuwar Reinaldi, et al researched the Comparison of Single Linkage, Complete Linkage, and Average Linkage Methods on Community Welfare in East Java, showing that the Average Linkage method provided the best grouping results based on the Silhouette Index [9]. Susiana Thaib, et al conducted research entitled Application of Hierarchical Cluster Analysis Using Average, Single, and Complete Linkage Methods on COVID-19 Patient Data in Indonesia (Case Study: IHSG Data 2016-2021) showing that the Average Linkage method is the best method for conducting grouping based on Cophenetic correlation values [10].…”

Quality Evaluation of Wind Energy Data with Complete Linkage Clustering

“…From customers' dataset, Single Linkage method could not clearly cluster shopping customers while Complete Linkage method and Ward method similarly clustered all customers into 5 groups. Yanuwar, Nurissaidah, Tony and Moh [12] applied three methods of Single Linkage method, Complete Linkage method and Average Linkage method to cluster people's community welfare in East Java. The results showed that methods of Complete Linkage and Average Linkage were really suitable methods to cluster people into 3 groups with data of their community welfare while Single Linkage again clustered most of people into one big group.…”

“…Researches [8][9][10][11][12][13][14][15][16] really show that the agglomerative hierarchical cluster methods can be applied to different types of datasets to cluster data into groups with multi-variables. However, Single Linkage method may not good to cluster dataset with closely values.…”

“…Since the secondary wind dataset [7] already informs the values of wind power in each alternative areas so that users can conveniently rank from the lowest wind energy area to the highest wind energy area, however, these datasets should be more useful if the data in this wind dataset can be clustered into groups with same wind quality in each group. Among many agglomerative hierarchical cluster methods [8][9][10][11][12][13][14][15][16], the simplest method without the effect of the closely data values and using together with other measure techniques should be Complete Linkage Method.…”