Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Intan Aidita Alfitrah
Universitas Sriwijaya
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
KLASIFIKASI KEPUTUSAN PEMBELIAN SKINCARE DI TIKTOK SHOP BERDASARKAN FAKTOR INFLUENCER MENGGUNAKAN ALGORITMA DECISION TREE Intan Aidita Alfitrah; Dinna Yunika Herdiyanti; Allsela Meiriza
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7293

Abstract

The development of TikTok Shop as a social commerce platform has increased the role of influencers in shaping skincare purchase decisions. However, the complexity of influencer-related factors makes it difficult to systematically identify purchase decision patterns. This study aims to explore the use of the Decision Tree algorithm to classify skincare purchase decisions on TikTok Shop based on influencer factors. Data were collected from 124 university students through a questionnaire survey. The purchase decision variable was constructed as a binary variable (purchase and non-purchase) by aggregating three questionnaire indicators. The independent variables consisted of six influencer constructs, namely credibility, popularity, trust, attractiveness, content quality, and promotion intensity. Model evaluation was conducted using stratified 5-fold cross-validation to reduce the risk of overfitting. The results indicate that the Decision Tree model achieved an average accuracy of 72.6%, exceeding the baseline accuracy of 62.1%. The precision, recall, and F1-score were 81.1%, 74.2%, and 76.9%, respectively, indicating moderate and stable classification performance. Feature importance analysis shows that influencer attractiveness has the highest relative contribution to the classification process, followed by credibility and popularity. This study demonstrates that Decision Tree can be used as an exploratory tool, with result interpretations being non-causal.  
Co-Authors Allsela Meiriza, Allsela Dinna Yunika Herdiyanti