Use of Hierarchical Clustering Method with Complexity Invariant Distance on Provincial Rice Prices in Indonesia

Mutiara Ishanifa

doi:10.21776/ub.jasds.2025.002.01.5

Authors

Mutiara Ishanifa Department of Statistics, Universitas Brawijaya, Malang, Indonesia

DOI:

https://doi.org/10.21776/ub.jasds.2025.002.01.5

Keywords:

Agglomerative Method, Complexity Invariant Distance (CID), Rice Prices, Time Series Data Cluster Analysis

Abstract

Cluster analysis of time series data used to group objects based on their characteristics or data patterns. Rice is one of the main food commodities for the people of Indonesia, so it is necessary to monitor and control rice prices by the government by considering the characteristics of each province. This study aims to determine the characteristics of each province based on data patterns in clusters formed based on rice prices using time series data cluster analysis. The data used is monthly data on rice prices in 34 provinces in Indonesia from January 2020 - December 2022. Clustering of time series data is done by hierarchical cluster analysis with agglomerative methods consisting of single linkage, complete linkage, average linkage, ward's method, and centroid method. The distance used for cluster analysis of time series data is Complexity Invariant Distance (CID). Determination of many clusters using the silhouette coefficient and measurement of accuracy using the cophenetic correlation coefficient. The results of clustering provinces in Indonesia based on rice prices resulted in 3 clusters. The first cluster consists of 1 province categorized as a cluster with high rice prices and the highest complexity value, the second cluster consists of 12 provinces categorized as a cluster with high rice prices and the lowest complexity value, and the third cluster consists of 21 provinces categorized as a cluster with low rice prices and low complexity value.

References

Abbasimehr. H.. & Bahrini. A. (2022). An Analytical Framework based on the Recency. Frequency. and Monetary Model and Time Series Clustering Techniques for Dynamic Segmentation. Expert Systems with Applications. 192. https://doi.org/10.1016/j.eswa.2021.116373

Adinugroho. W. (2021). Pendekatan Clustering Time Series pada Peramalan Harga Minyak Goreng. Jurnal Ilmiah Populer MEDIAN (Vol. 4).

Adnyani. L. P. W.. & Sihombing. P. R. (2021). Analisis Cluster Time Series dalam Pengelompokan Provinsi di Indonesia Berdasarkan Nilai PDRB. Bayesian. 1(1). 47–53. http://bayesian.lppmbinabangsa.id/index.php/home

Amato. F.. Laib. M.. Guignard. F.. & Kanevski. M. (2020). Analysis of Air Pollution Time Series Using Complexity-Invariant Distance and Information Measures. Physica A: Statistical Mechanics and its Applications. 547. https://doi.org/10.1016/j.physa.2020.124391

Batista. G. E. A. P. A.. Wang. X.. & Keogh. E. J. (2011). A complexity-Invariant distance Measure for Time Series. Proceedings of the 11th SIAM International Conference on Data Mining. SDM 2011. 699–710. https://doi.org/10.1137/1.9781611972818.60

Charrad. M.. Ghazzali. N.. Boiteau. V dan Niknafs. A.. 2014. An R Package for Determining the Relevant Number of Clusters in a Data set. Jurnal of Statistical Software. 61.6.

Giusti. R.. & Batista. G. E. A. P. A. (2013). An Empirical Comparison of Dissimilarity Measures for Time Series Classification. Proceedings - 2013 Brazilian Conference on Intelligent Systems. BRACIS 2013. 82–88. https://doi.org/10.1109/BRACIS.2013.22

Hair. J. F.. Black. W. C.. & Babin. B. J. (2010). Multivariate Data Analysis 7th. New Jersey: Pearson Prentice Hall.

Hermawan. I. (2013). Analisis Perdagangan Beras dan Ketahanan Pangan di Negara-negara Asia Tenggara. Jurnal Politica Dinamika Masalah Politik Dalam Negeri dan Hubungan Internasional. 4(2). http://irri.org/index.php?option=

Johnson. W.. & Wichern. (2007). Applied Multivariate Statistical Analysis 6th Edition.

Mattjik. A. A.. & Sumertajaya. I. M. (2011). Sidik Peubah Ganda dengan Menggunakan SAS. Bogor: IPB PRESS.

Rani. S.. & Sikka. G. (2012). Recent Techniques of Clustering of Time Series Data: A Survey. International Journal of Computer Applications. 52(15). 1–9. https://doi.org/10.5120/8282-1278

Saraçli. S.. Doǧan. N.. & Doǧan. I. (2013). Comparison of Hierarchical Cluster Analysis Methods by Cophenetic Correlation. Journal of Inequalities and Applications. 2013. https://doi.org/10.1186/1029-242X-2013-203

Shang. D.. Shang. P.. & Liu. L. (2019). Multidimensional Scaling Method for Complex Time Series Feature Classification based on Generalized Complexity-Invariant Distance. Nonlinear Dynamics. 95(4). 2875–2892. https://doi.org/10.1007/s11071-018-4728-6

Silva. A. R.. & Dias. C. T. dos S. (2013). A Cophenetic Correlation Coefficient for Tocher’s Method. Pesquisa Agropecuaria Brasileira. 48(6). 589–596. https://doi.org/10.1590/S0100-204X2013000600003

Ulinnuha. M.. M Afendi. F.. & Sumertajaya. I. M. (2022). Study of Clustering Time Series Forecasting Model for Provincial Grouping in Indonesia Based on Rice Price. Indonesian Journal of Statistics and Its Applications. 6(1). 50–62. https://doi.org/10.29244/ijsa.v6i1p50-62