Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal Software Engineering and Computer Science (IJSECS)
Aldila Cinderatama, Toga
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
AutoClusterAPI: A Lightweight Backend Framework for Automated Unsupervised Clustering Pipelines Yunhasnawa, Yoppy; Windawati, Atif; Aldila Cinderatama, Toga; Abdullah, Moch. Zawaruddin; Nur Hamdana, Elok
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.5997

Abstract

This study presents AutoClusterAPI, a lightweight and extensible backend system designed to simplify and accelerate unsupervised clustering workflows. The system addresses a recurring problem in data analysis practice: many practitioners need rapid clustering capabilities but lack the programming or statistical background required to build complete pipelines from scratch. AutoClusterAPI provides an automated, endpoint-driven solution that allows users to perform every stage of clustering — from data loading and cleaning to feature preparation, algorithm execution, profiling, and visualization — through standard HTTP requests. The system is built using Python and the FastAPI web framework, supports eight clustering algorithms, and includes automated preprocessing alongside PCA-based visualization. Functional testing confirms that all endpoints behave correctly under both valid and invalid inputs, establishing the reliability of the system. A case study using a customer segmentation dataset further demonstrates its practical utility, showing that AutoClusterAPI can efficiently generate meaningful cluster structures and interpretable visual outputs. The system offers an accessible yet configurable environment for rapid clustering analysis and establishes a basis for future extensions and real-world deployment.
Co-Authors Elok Nur Hamdana Moch Zawaruddin Abdullah Windawati, Atif Yoppy Yunhasnawa