Overview

Original Research

GEOGRAPHICAL BIG DATA ANALYSIS OF HOUSE PRICE IN SHENZHEN FOR ADAPTATION IN MALAYSIA

AHMAD FIRDHAUS ARHAM 1, ABDUL HADI NAWAWI 2, SATHEES BALACHANDRU 3, MUHAMMAD FIRDAUS AZIZ 4, JAMSARI ALIAS 5, and AHMAD NAZRUL HAKIMI IBRAHIM 6.

Vol 19, No 01 ( 2024 )   |  DOI: 10.5281/zenodo.10548673   |   Author Affiliation: School of Liberal Studies (CITRA-UKM), Universiti Kebangsaan Malaysia, Malaysia, Centre of Studies for Estate Management, Faculty of Architecture, Planning and Surveying, Universiti Teknologi MARA, Shah Alam, Malaysia 1; Centre of Studies for Estate Management, Faculty of Architecture, Planning and Surveying, Universiti Teknologi MARA, Shah Alam, Malaysia 2; School of Liberal Studies (CITRA-UKM), Universiti Kebangsaan Malaysia, Malaysia 3,4,5; Department of Civil Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Malaysia. Sustainable Urban Transport Research Centre, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Malaysia 6.   |   Licensing: CC 4.0   |   Pg no: 718-727   |   Published on: 18-01-2024

Abstract

This paper will analyze "Understanding Housing Prices Using Geographical Big Data: A Case Study in Shenzhen" by Jiang et al. (2022) and explain how the methods used in this paper can form an evidence-based understanding of house prices in Malaysia. Understanding the relationship between housing prices and geographic big data trends is critical to developing successful housing policies and urban development strategies. The increased demand for housing has raised concerns about housing price discrepancies, which affect quality of life and the economy. Previous studies have analyzed the price of housing costs also related to geographic and environmental factors, resulting in price differences in each location. However, the complex network of cities makes it difficult to use proximity to the city center to explain urban housing costs. Geographical statistics, exploratory geographic data analysis and other methods have been used to measure geographic autocorrelation with housing prices to improve housing price models. Research by Jiang et al., this is used as the main reference in evaluating big geographic data to predict and analyze real estate prices. Commercial development, transportation, infrastructure, location, education, environment, and level of use affect real estate prices. The geographic distribution of house price data is examined using Moran's I and geographic tracers, while XGBoost lists the factors that influence house prices. This study is important to help Malaysian property developers by using this strategy in determining house prices and suitable residential locations.

Keywords

Housing Prices, Geographical Data, Big Data, Shenzhen, Malaysia.