Discovering Consumer Loyalty Insights in Indonesia's Local Cosmetic Brands: A Data Mining Approach Using Clustering and Classification

Irfani, Salsabila Fauzia (2025) Discovering Consumer Loyalty Insights in Indonesia's Local Cosmetic Brands: A Data Mining Approach Using Clustering and Classification. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5031211022-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy

Abstract

The Indonesian beauty industry is thriving, allowing local cosmetic brands to compete effectively in a dynamic market. This study examines consumer retention and advocacy by analyzing user reviews from the SOCO platform. Utilizing data mining algorithms, it evaluates key factors such as satisfaction ratings, polarity scores, repurchase intentions, and willingness to recommend, focusing on the top-reviewed products in face, eyes, and lips categories from January 2023 to September 2024. Products were clustered into three categories which are Low, Moderate, and High Loyalty Products employing K-Means Clustering. High Loyalty Products exhibited strong repurchase and recommendation rates, driven by superior packaging and pigmentation, while Low Loyalty Products highlighted areas for improvement in texture and long wear. Random Forest models emerged as the best algorithm, with all non-textual consumer satisfaction ratings, product name, sub-category, age range, and sentiment as input features to predict consumer loyalty. This research provides actionable insights into consumer loyalty drivers, helping local cosmetic brands optimize marketing strategies, reduce costs, and strengthen retention in a competitive industry.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Classification, Clustering, Consumer Loyalty, Indonesia's Local Brands
Divisions:	Faculty of Creative Design and Digital Business (CREABIZ) > Business Management > 61205-(S1) Undergraduate Thesis
Depositing User:	Salsabila Fauzia Irfani
Date Deposited:	09 Feb 2026 07:33
Last Modified:	09 Feb 2026 07:33
URI:	http://repository.its.ac.id/id/eprint/120945

Actions (login required)

View Item