Claim Missing Document
Check
Articles

Found 21 Documents
Search

Integration of K-Means Clustering, Random Forest, and RFM Analysis for Optimizing Consumer Segmentation in Digital Advertising Strategies Joang Ipmawati; Kusnawi
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 01 (2026): JANUARY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i01.2548

Abstract

In the era of data-driven marketing, accurate consumer segmentation is essential to improve the precision and impact of digital advertising. This study aims to produce more accurate consumer segmentation to support more targeted digital marketing strategies. The methods used include K-Means Clustering to group users based on digital behavior, RFM Analysis to evaluate user loyalty and interaction value with advertisements, and Random Forest to identify key factors influencing segmentation. The dataset includes demographic and behavioral information such as age, gender, income level, online duration, and interaction with digital ads. The results show that using five clusters (K=5) in K-Means Clustering yields optimal segmentation. RFM Analysis successfully categorizes users based on loyalty and engagement, while Random Forest identifies Click-Through Rate (CTR), Likes and Reactions, and Time Spent Online as the most influential variables in segmentation. This research contributes to improving the effectiveness of digital advertising campaigns and supports data-driven decision-making. The findings are significant for understanding consumer behavior patterns more deeply and for designing more efficient and relevant marketing strategies.