Data Mining for Analyzing Consumer Segmentation: Identifying Consumer Preference Patterns Using the Fuzzy C-Means Clustering on Halal Products

Abstract

Halal products are increasingly popular worldwide, not only in Muslim-majority countries but also in non-Muslim nations.  The global halal market exceeds USD 650 million annually, emphasizing the importance of halal certification, particularly in Indonesia as the world’s largest Muslim-majority country. This research aims to cluster consumers of halal meat products by analyzing factors influencing consumer behavior in purchasing certified halal beef and chicken. The study employs the Fuzzy C-Means (FCM) clustering algorithm on 176 respondents’ questionnaire data consisting of 36 parameters. The experiment was performed using Google Colab with a maximum of 1000 iterations, error tolerance of 0.0001, and fuzziness coefficient m = 2.4. Results show that two optimal clusters were formed, with a Partition Coefficient Index (PCI) value of 0.9993, indicating excellent clustering quality. The first cluster consists primarily of young consumers aged 15–24 with lower spending, while the second cluster includes adults aged 35–54 with higher income. Both groups prioritize halal certification and logo visibility when choosing meat products. The findings provide insights for halal product retailers and policymakers to enhance halal product distribution, certification support, and marketing strategies in Indonesia.