Land Price Modelling with Radial Basis Function (Case Study: Utan Kayu Selatan Village, East Jakarta)

Sawitri Subiyanto; Hana Sugiastu Firdaus; Nahar Dito Utama Giardi

doi:10.30871/jagi.v5i1.2637

Sawitri Subiyanto Departement of Geodetic Engineering, Faculty of Engineering, Diponegoro University Jl. Prof. Sudarto, SH, Tembalang, Semarang Telp.(024)76480785, 76480788, Indonesia
Hana Sugiastu Firdaus Departement of Geodetic Engineering, Faculty of Engineering, Diponegoro University Jl. Prof. Sudarto, SH, Tembalang, Semarang Telp.(024)76480785, 76480788, Indonesia
Nahar Dito Utama Giardi Departement of Geodetic Engineering, Faculty of Engineering, Diponegoro University Jl. Prof. Sudarto, SH, Tembalang, Semarang Telp.(024)76480785, 76480788, Indonesia

DOI: https://doi.org/10.30871/jagi.v5i1.2637

Keywords: Land Price, Mathematical Model, RBF

Abstract

The price of land is an important matter that needs to be assessed by stakeholders. The study of land prices has an important role in seeing the stability of the property market. Several factors affect the property business such as accessibility, public facilities and social facilities. Utan Kayu Selatan is the largest village in Matraman Sub-District with an area of 1,12 kilometers. The potential of the property business is very tempting for investors to property developers. One of the economic sector developments is Utan Kayu Raya Road, which can increase land prices in the surrounding area. The factors that influence land prices can be analyzed through several approaches such as regression, mass appraisal and other. In this study, the method used in estimating land prices is the Radial Basis Function (RBF), by looking at the relationship between the distance of plot to roads, public facilities and social facilities. Modeling is carried out based on samples determined on ZNT and NJOP land prices. Furthermore, the calculation of the distance is done by using network analysis. As a result, the RMSE value for the NJOP RBF model and the ZNT RBF model is IDR 1.179.839 and IDR 2.972.345. Meanwhile, the CoV values for both models were 6.2% and 6%. In the comparison of ZNT price predictions with market prices, the highest difference is IDR 13.119.915 and the lowest difference is IDR 537.009. While on the NJOP price prediction, the highest difference is IDR 15.797.583 and the lowest difference is IDR 291.270.

Downloads

Download data is not yet available.

References

Amirin, T. (2011). Populasi dan Sampel 4: Ukuran Sampel Rumus Slovin. In Jakarta: Erlangga

Badan Pusat Statistik Jakarta Timur. (2018). Kecamatan Matraman Dalam Angka 2018. In Jakarta

Buwana, A A. (2006). Prediksi Penjualan PT. Usaha Varia Beton Menggunakan Artificial Neural Network. In Surabaya: Institut Teknologi Surabaya

Closest Facility Analysis [WWW Document], (2020). [WWW Document]. ArcGIS Desktop. URL https://desktop.arcgis.com/en/arcmap/latest/extensions/network-analyst/closest-facility.htm (accessed 08.21.20).

Fasshauer, G. F. (2007). Meshfree Approximation Methods with MATLAB (Interdisciplinary Mathematical Sciences). http://www.amazon.com/Meshfree-Approximation-Interdisciplinary-Mathematical-Sciences/dp/9812706348

Harjanto, B., & Hidayati, W. (2003). Konsep Dasar Penilaian Properti. In Yogyakarta: BPFE.

Husna. (2016). Estimasi Harga Tanah Menggunakan Radial Basis Function (RBF). (thesis). In Aceh: Universitas Syiah Kuala

International Association of Assessing Officers. (2013). Standard on Ratio Studies (Issue April). http://www.iaao.org/uploads/standard_on_ratio_studies.pdf

Linne, M. R., S. M. Kane & G. Dell. (2000). A Guide to Appraisal Valuation Modeling. In USA: Appraisal Institute

Mengupas Tren Pasar Properti Jakarta Timur [WWW Document], (2018). [WWW Document]. rumah.com. URL https://www.rumah.com/areainsider/jakarta-timur/article/mengupas-tren-pasar-properti-jakarta-timur-2133 (accessed 10.21.20).

Sampathkumar, V., Santhi, M. H., & Vanjinathan, J. (2015). Forecasting the Land Price Using Statistical and Neural Network Software. Procedia Computer Science, 57, 112–121. https://doi.org/10.1016/j.procs.2015.07.377

Tejada, J., & Punzalan, J. (2012). On the misuse of Slovin's formula. The Philippine Statistician, 61(1), 129–136.

Truong, Q., Nguyen, M., Dang, H., & Mei, B. (2020). Housing Price Prediction via Improved Machine Learning Techniques. Procedia Computer Science, 174(2019), 433–442. https://doi.org/10.1016/j.procs.2020.06.111

Wiyanti, D. T., & Pulungan, R. (2012). Peramalan Deret Waktu Menggunakan Model Fungsi Basis Radial (Rbf) Dan Auto Regressive Integrated Moving Average (Arima). Jurnal MIPA, 35(2), 175–182.