Pembangunan Model Klasifikasi untuk Menilai Lokasi Strategis Usaha Laundry di Surabaya Berdasarkan Analisis Geospasial dan Data Open-Source

Riznov, Briandana (2026) Pembangunan Model Klasifikasi untuk Menilai Lokasi Strategis Usaha Laundry di Surabaya Berdasarkan Analisis Geospasial dan Data Open-Source. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032231214-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Industri jasa cuci pakaian di Indonesia terus mengalami pertumbuhan pesat seiring perubahan gaya hidup masyarakat urban yang semakin praktis. Kota Surabaya, sebagai salah satu kota metropolitan dengan kepadatan penduduk tinggi dan aktivitas ekonomi yang dinamis, menjadi wilayah potensial bagi pengembangan bisnis laundry. Namun, banyak pelaku usaha mengalami kegagalan akibat pemilihan lokasi yang kurang tepat, sehingga dibutuhkan pendekatan berbasis data untuk mengevaluasi kelayakan lokasi usaha yang telah ada. Penelitian ini bertujuan untuk membangun model klasifikasi berbasis analisis geospasial dalam menilai apakah suatu lokasi usaha laundry eksisting di Surabaya tergolong strategis atau tidak strategis. Data penelitian diperoleh dari sumber open-source seperti Google Maps API, OpenStreetMap (OSM), dan data sekunder dari Badan Pusat Statistik (BPS), yang mencakup variabel spasial, demografis, dan ekonomi. Proses analisis dilakukan melalui tahapan pembersihan data, rekayasa fitur, penyeimbangan data (SMOTE), penerapan algoritma klasifikasi, serta evaluasi performa model menggunakan metrik Accuracy, Precision, Recall, F1-score, dan ROC-AUC. Hasil penelitian menunjukkan bahwa dari lima metode klasifikasi yang digunakan Logistic Regression, Decision Tree, Naive Bayes, k-Nearest Neighbor (k-NN), dan Random Forest algoritma Random Forest memberikan performa terbaik dengan nilai akurasi 90,1% dan ROCAUC 0,957. Visualisasi hasil klasifikasi disajikan dalam bentuk peta interaktif dan dashboard evaluatif, yang memungkinkan analisis spasial terhadap persebaran lokasi strategis. Penelitian ini berkontribusi dalam menyediakan kerangka evaluasi berbasis data dan geospasial yang dapat dimanfaatkan oleh pelaku usaha maupun pengambil kebijakan untuk mendukung keputusan lokasi bisnis yang lebih objektif dan terukur.
=========================================================================================================================
The laundry service industry in Indonesia has shown rapid growth in line with the increasingly practical lifestyle of urban communities. As one of Indonesia’s major metropolitan cities with a high population density and dynamic economic activity, Surabaya offers strong potential for laundry business development. However, many entrepreneurs fail due to improper location selection, indicating the need for a data-driven approach to evaluate the feasibility of existing business locations. This study aims to develop a geospatial-based classification model to determine whether an existing laundry business location in Surabaya is categorized as strategic or non-strategic. The research data were collected on May 7, 2025, from various open-source platforms, including Google Maps API, OpenStreetMap (OSM), and secondary data from the Central Bureau of Statistics (BPS). The dataset covers spatial, demographic, and economic variables. The analytical process involved data preprocessing, feature engineering, data balancing (SMOTE), implementation of five classification algorithms, and model evaluation using performance metrics such as Accuracy, Precision, Recall, F1-score, and ROC-AUC. The results indicate that among the five algorithms tested — Logistic Regression, Decision Tree, Naive Bayes, k-Nearest Neighbor (k-NN), and Random Forest — the Random Forest algorithm achieved the best performance, with an accuracy of 90.1% and an ROC-AUC of 0.957. The classification results were visualized through an interactive map and analytical dashboard, enabling spatial interpretation of strategic business areas. This study contributes to developing a data- and geospatial-based evaluation framework that can be utilized by entrepreneurs and policymakers to support evidence-based business location decisions.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Laundry, Analisis Geospasial, Klasifikasi, Random Forest, Data Open-Source, Lokasi Strategis, Laundry, Geospatial Analysis, Classification, Random Forest, Open-Source Data, Strategic Location
Subjects:	T Technology > T Technology (General)
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Briandana Riznov
Date Deposited:	19 Jan 2026 06:38
Last Modified:	27 Jan 2026 07:00
URI:	http://repository.its.ac.id/id/eprint/129714

Actions (login required)

View Item