Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Artificial Intelligence and Digital Business
Wahyuni Wahyuni
Universitas Pamulang
Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Implementation Of the C4.5 Algorithm for Web-Based Skincare Sales Classification at Sintia Distributor SR12 Wahyuni Wahyuni; Elfi Fauziah
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 2 (2026): Mei-Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i2.12628

Abstract

Sintia Distributor SR12 is a business that distributes various skincare products. Sales records available at the store had not been optimally utilized to objectively identify products with high and low sales. This condition could affect inventory planning and sales evaluation because product performance was still assessed through manual observation. This study aimed to implement the C4.5 algorithm in a web-based system for classifying skincare product sales. Data were collected through observation, interviews, and literature review. The system was developed using Python Flask, MySQL, HTML, CSS, Bootstrap, JavaScript, and Chart.js. The classification process consisted of selecting a sales period, combining product and sales data, calculating the average quantity sold, forming class labels, calculating entropy, gain, split information, and gain ratio, and generating classification rules. Testing was conducted using Black Box Testing, White Box Testing with the Basis Path technique, and a user response questionnaire. The implementation processed 31 product records, consisting of 13 Best-Selling products and 18 Non-Best-Selling products. The initial entropy value was 0.981, while the quantity-sold attribute obtained a gain ratio of 1.000. All main system functions and internal classification paths operated according to the designed scenarios. User response testing involving five respondents and ten questions produced a score of 95.60%, categorized as Very Good. The developed system can assist the store in managing sales data and presenting period-based product classification information for inventory and sales strategy evaluation.
Co-Authors Elfi Fauziah