Pembangunan Model Klasifikasi untuk Menilai Lokasi Strategis Usaha Laundry Berdasarkan Analisis Geospasial dan Data Open-Source: Development of a Classification Model to Evaluate Strategic Laundry Business Locations Using Geospatial and Open-Source Data

Briandana Riznov; Bagus Jati Santoso

doi:10.57152/malcom.v6i1.2358

Authors

Briandana Riznov Institut Teknologi Sepuluh Nopember
Bagus Institut Teknologi Sepuluh Nopember

DOI:

https://doi.org/10.57152/malcom.v6i1.2358

Keywords:

Analisis Geospasial, Bisnis Strategis, Data Open-Source, Model Klasifikasi, Random Forest

Abstract

Industri jasa cuci pakaian di Indonesia terus mengalami pertumbuhan pesat seiring perubahan gaya hidup masyarakat urban yang semakin praktis. Namun, banyak pelaku usaha mengalami kegagalan akibat pemilihan lokasi yang kurang tepat, sehingga diperlukan pendekatan berbasis data untuk mengevaluasi kelayakan lokasi usaha secara objektif. Penelitian ini bertujuan untuk mengembangkan model klasifikasi berbasis analisis geospasial dan data open-source guna menilai apakah lokasi usaha laundry eksisting di Surabaya tergolong strategis atau tidak strategis. Data penelitian dikumpulkan dari Google Maps API, OpenStreetMap (OSM), dan Badan Pusat Statistik (BPS), yang mencakup indikator spasial, demografis, dan ekonomi. Proses analisis meliputi pembersihan data, rekayasa fitur, penyeimbangan data dengan SMOTE, serta penerapan lima algoritma klasifikasi Logistic Regression, Decision Tree, Naive Bayes, k-Nearest Neighbor, dan Random Forest dengan evaluasi menggunakan metrik Accuracy, Precision, Recall, F1-score, dan ROC-AUC. Hasil penelitian menunjukkan bahwa algoritma Random Forest memberikan performa terbaik dengan akurasi 90,1% dan ROC-AUC 0,957. Faktor kepadatan penduduk, kedekatan dengan permukiman, dan jumlah kompetitor terbukti paling berpengaruh terhadap tingkat strategis lokasi. Penelitian ini berkontribusi dalam menyediakan kerangka evaluasi berbasis data dan geospasial yang dapat digunakan sebagai dasar pengambilan keputusan bisnis yang lebih objektif, terukur, dan adaptif terhadap dinamika perkotaan.

Downloads

Download data is not yet available.

References

M. Georgati, H. S. Hansen, and C. Keßler, “Random Forest Variable Importance Measures for Spatial Dynamics: Case Studies from Urban Demography,” ISPRS Int J Geoinf, vol. 12, no. 11, p. 987, 2023, doi: 10.3390/ijgi12110987.

Z. Zheng, T. Morimoto, and Y. Murayama, “A GIS-Based Bivariate Logistic Regression Model for the Site-Suitability Analysis of Parcel-Pickup Lockers: A Case Study of Guangzhou, China,” ISPRS Int J Geoinf, vol. 10, no. 10, p. 871, 2021, doi: 10.3390/ijgi10100871.

J. Zhao, B. Zong, and L. Wu, “Site Selection Prediction for Coffee Shops Based on Multi-Source Space Data Using Machine Learning Techniques,” ISPRS Int J Geoinf, vol. 12, no. 8, p. 456, 2023, doi: 10.3390/ijgi12080456.

F. Gao et al., “Location differs between traditional and new retail: A comparison analysis of Starbucks and Luckin Coffee using machine learning,” Cities, vol. 158, 2025, doi: 10.1016/j.cities.2024.104123.

M. D. Lagzi, S. M. Sajadi, and M. Taghizadeh-Yazdi, “A hybrid stochastic data envelopment analysis and decision tree for performance prediction in retail industry,” Journal of Retailing and Consumer Services, vol. 80, 2024, doi: 10.1016/j.jretconser.2024.103954.

J. Lu, X. Zheng, E. Nervino, Y. Li, Z. Xu, and Y. Xu, “Retail store location screening: A machine learning-based approach,” Journal of Retailing and Consumer Services, vol. 77, 2024, doi: 10.1016/j.jretconser.2023.103630.

T. Samal and A. Ghosh, “Ensemble-based predictive analytics for demand forecasting in multi-channel retailing,” Expert Syst Appl, vol. 299, p. 130212, Mar. 2026, doi: 10.1016/j.eswa.2025.130212.

Y. Chen, K. Xu, Y. He, and Q. Chen, “Utilitarian or experiential? Divergent location strategies of the rural coffee retail in the Hangzhou metropolitan area,” Journal of Retailing and Consumer Services, vol. 88, Jan. 2026, doi: 10.1016/j.jretconser.2025.104540.

J. Lu, X. Zheng, E. Nervino, Y. Li, Z. Xu, and Y. Xu, “Retail store location screening: A machine learning-based approach,” Journal of Retailing and Consumer Services, vol. 77, Mar. 2024, doi: 10.1016/j.jretconser.2023.103620.

L. Dong, J. Wu, and L. Zhang, “A hybrid machine learning approach for urban commercial zone classification,” Comput Environ Urban Syst, vol. 97, p. 101882, 2022, doi: 10.1016/j.compenvurbsys.2022.101882.

X. Zhu, Q. Li, and Y. Li, “Predicting optimal business locations from multi-source geospatial data,” Land (Basel), vol. 12, no. 4, p. 845, 2023, doi: 10.3390/land12040845.

J. Cheng and M. Adepeju, “Spatial machine learning for point-of-interest demand estimation,” Transactions in GIS, vol. 26, no. 3, pp. 1159–1177, 2022, doi: 10.1111/tgis.12903.

J. Kang and H. Park, “POI-based business success prediction using ensemble classification,” Expert Syst Appl, vol. 218, p. 119556, 2023, doi: 10.1016/j.eswa.2022.119556.

C. Yi and B. Huang, “Spatial clustering and hotspot analysis for commercial site selection,” Environment and Planning B, vol. 48, no. 5, pp. 1243–1260, 2021, doi: 10.1177/2399808320930878.

Y. Li, J. Wang, and X. Huang, “Urban commercial hotspot prediction using ensemble geospatial models,” Remote Sens (Basel), vol. 16, no. 3, p. 612, 2024, doi: 10.3390/rs16030612.

S. Ghosh and M. Das, “Assessment of service facility locations using GIS-based spatial analytics,” GeoJournal, vol. 85, pp. 1515–1534, 2020, doi: 10.1007/s10708-019-09992-y.

Y. Xu, S. Li, and X. Qiu, “Evaluating urban service accessibility using machine learning and GIS,” Applied Geography, vol. 122, p. 102246, 2020, doi: 10.1016/j.apgeog.2020.102246.

S. Hong, S. Lee, and J. Kim, “Retail location prediction using deep learning and geospatial big data,” Sustainability, vol. 13, no. 6, p. 3241, 2021, doi: 10.3390/su13063241.

D. Zhu, C. Cheng, W. Zhai, Y. Li, S. Li, and B. Chen, “Multiscale spatial polygonal object granularity factor matching method based on BPNN,” ISPRS Int J Geoinf, vol. 10, no. 2, Feb. 2021, doi: 10.3390/ijgi10020075.

D. Klimonová, V. Anderková, F. Babi?, and L. T. Majnaric, “Decision Support System Improving the Interpretability of Generated Tree-Based Models,” Acta Electrotechnica et Informatica, vol. 22, no. 2, pp. 27–33, Jun. 2022, doi: 10.2478/aei-2022-0009.

T. Pranckevi?ius and V. Marcinkevi?ius, “Comparison of Naive Bayes, Random Forest, Decision Tree, Support Vector Machines, and Logistic Regression Classifiers for Text Reviews Classification,” Baltic Journal of Modern Computing, vol. 5, no. 2, 2017, doi: 10.22364/bjmc.2017.5.2.05.