ANALISIS PERILAKU PEMBELIAN AUDIENS TIKTOK MELALUI KLASTERISASI PREFERENSI KONTEN DENGAN ALGORITMA K-MEANS

Abstract

The rapid growth of TikTok as a digital marketing platform has created a need to understand how content variation influences user purchasing behavior. This study is motivated by the lack of information regarding audience responses to live streaming content, particularly in the context of purchase decision-making. The objective of this research is to identify audience segmentation patterns on TikTok based on content preferences and how these relate to purchasing decisions, using the account @takiboutique as a case study. A quantitative research approach was employed, utilizing an online survey distributed to 99 randomly selected respondents. Data were analyzed using the K-Means clustering algorithm to group respondents based on dominant factors influencing their buying decisions. The clustering results revealed three main audience segments. The first cluster (53%) prioritizes creative and interactive marketing strategies. The second cluster (34%) considers price as the most influential factor in purchasing decisions. The third cluster (12%) highlights product quality as the primary consideration. These findings indicate that audience preferences for promotional content are diverse, requiring marketing communication strategies to be tailored to the characteristics of each segment. The application of the K-Means algorithm has proven effective in profiling consumers to support more adaptive and targeted digital marketing strategies.