Monitoring housing rental prices based on social media:An integrated approach of machine-learning algorithms and hedonic modeling to inform equitable housing policies

Hu, Lirong; He, Shenjing; Han, Zixuan; He, Xiaodong; Su, Shiliang; Wang, Min; Cai, Zhongliang

doi:10.1016/j.landusepol.2018.12.030

Cited by 163 publications

(103 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MLP is a forward-structure artificial neural network (ANN) trained by the backpropagation method, designed to map a set of input vectors to a set of output vectors [61]. ANN can be simply defined as a massively parallel distributed computational device consisting of processing units, also called neurons or nodes, which are organized in a couple of layers.…”

Section: Classification and Validationmentioning

confidence: 99%

A Comparative Assessment of Machine-Learning Techniques for Land Use and Land Cover Classification of the Brazilian Tropical Savanna Using ALOS-2/PALSAR-2 Polarimetric Images

et al. 2019

View full text Add to dashboard Cite

This study proposes a workflow for land use and land cover (LULC) classification of Advanced Land Observing Satellite-2 (ALOS-2) Phased Array type L-band Synthetic Aperture Radar-2 (PALSAR-2) images of the Brazilian tropical savanna (Cerrado) biome. The following LULC classes were considered: forestlands; shrublands; grasslands; reforestations; croplands; pasturelands; bare soils/straws; urban areas; and water reservoirs. The proposed approach combines polarimetric attributes, image segmentation, and machine-learning procedures. A set of 125 attributes was generated using polarimetric ALOS-2/PALSAR-2 images, including the van Zyl, Freeman–Durden, Yamaguchi, and Cloude–Pottier target decomposition components, incoherent polarimetric parameters (biomass indices and polarization ratios), and HH-, HV-, VH-, and VV-polarized amplitude images. These attributes were classified using the Naive Bayes (NB), DT J48 (DT = decision tree), Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) algorithms. The RF, MLP, and SVM classifiers presented the most accurate performances. NB and DT J48 classifiers showed a lower performance in relation to the RF, MLP, and SVM. The DT J48 classifier was the most suitable algorithm for discriminating urban areas and natural vegetation cover. The proposed workflow can be replicated for other SAR images with different acquisition modes or for other types of vegetation domains.

show abstract

Section: Classification and Validationmentioning

confidence: 99%

A Comparative Assessment of Machine-Learning Techniques for Land Use and Land Cover Classification of the Brazilian Tropical Savanna Using ALOS-2/PALSAR-2 Polarimetric Images

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Recent urban housing prices studies have shown the advantage of ensemble learning algorithms over traditional methods [28,38]. Hu compared the performance of six machine learning algorithms in monitoring housing rental prices and found that ExtraTrees and RFR get better results [39]. However, because the nature of ensemble learning models are not interpretable models, almost all of these studies only range the importance when measuring the impacts of a housing characteristic on housing prices.…”

Section: Introductionmentioning

confidence: 99%

Measuring Impacts of Urban Environmental Elements on Housing Prices Based on Multisource Data—A Case Study of Shanghai, China

Chen

Yao

Zhu

et al. 2020

IJGI

View full text Add to dashboard Cite

Diverse urban environmental elements provide health and amenity value for residents. People are willing to pay a premium for a better environment. Thus, it is essential to assess the benefits and values of these environmental elements. However, limited by the interpretability of the machine learning model, existing studies cannot fully excavate the complex nonlinear relationships between housing prices and environmental elements, as well as the spatial variations of impacts of urban environmental elements on housing prices. This study explored the impacts of urban environmental elements on residential housing prices based on multisource data in Shanghai. A SHapley Additive exPlanations (SHAP) method was introduced to explain the impacts of urban environmental elements on housing prices. By combining the ensemble learning model and SHAP, the contributions of environmental characteristics derived from street view data and remote sensing data were computed and mapped. The experimental results show that all the urban environmental characteristics account for 16 percent of housing prices in Shanghai. The relationships between housing prices and two green characteristics (green view index from street view data and urban green coverage rate from remote sensing) are both nonlinear. Shanghai's homebuyers are willing to pay a premium for green only when the green view index or urban green coverage rate are of higher value. However, there are significant differences between the impacts of the green view index and urban green coverage rate on housing prices. The sky view index has a negative influence on housing prices, which is probably because the high-density and high-rise residential area often has better living facilities. Residents in Shanghai are willing to pay a premium for high urban water coverage. The case of Shanghai shows that the proposed framework is practical and efficient. This framework is believed to provide a tool to inform the decisions of housing buyers, property developers and policies concerning land-selling and buying, property development and urban environment improvement.

show abstract

“…According to the 2017 American Housing Survey, more renters in urbanized areas found their current homes through a site like Craigslist than through any other information channel. Housing practitioners and researchers, in turn, increasingly collect online listings to assess market supply in the smart cities paradigm of monitoring urban conditions through streams of user-generated data (Boeing et al, 2019;Hu et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Online rental housing market representation and the digital reproduction of urban inequality

Boeing

2019

Environ Plan A

View full text Add to dashboard Cite

As the rental housing market moves online, the Internet offers divergent possible futures: either the promise of more-equal access to information for previously marginalized homeseekers, or a reproduction of longstanding information inequalities. Biases in online listings' representativeness could impact different communities' access to housing search information, reinforcing traditional information segregation patterns through a digital divide. They could also circumscribe housing practitioners' and researchers' ability to draw broad market insights from listings to understand rental supply and affordability. This study examines millions of Craigslist rental listings across the US and finds that they spatially concentrate and over-represent whiter, wealthier, and better-educated communities. Other significant demographic differences exist in age, language, college enrollment, rent, poverty rate, and household size. Most cities' online housing markets are digitally segregated by race and class, and we discuss various implications for residential mobility, community legibility, gentrification, housing voucher utilization, and automated monitoring and analytics in the smart cities paradigm. While Craigslist contains valuable crowdsourced data to better understand affordability and available rental supply in real-time, it does not evenly represent all market segments. The Internet promises information democratization, and online listings can reduce housing search costs and increase choice sets. However, technology access/preferences and information channel segregation can concentrate such information-broadcasting benefits in already-advantaged communities, reproducing traditional inequalities and reinforcing residential sorting and segregation dynamics. Technology platforms like Craigslist construct new institutions with the power to shape spatial economies, human interactions, and planners' ability to monitor and respond to urban challenges. Prospective renters heterogeneously rely on a constellation of information sources to identify available units, including websites, newspapers, agents/brokers, property for-rent signs, and word of mouth. Krysan and Crowder (2017) theorize a two-stage search process in which homeseekers decide which neighborhoods to search and then choose which units within them to consider, emphasizing the importance of information supplies. Rae (2015) contends that the Internet has emerged as the first port of call for such searches, but online information also impacts the second stage by rendering individual units and in turn neighborhoods more legible and accessible to seekers. As the Internet constitutes an ever-increasing share of the rental housing information supply, different communities' access to information and capacity to find housing depend both on listings' representativeness and communities' abilities/interests in engaging with these platforms. This can be considered from the supplyside (i.e., the supply of information by landlords, managers, and brokers) and the demand-side (i.e...

show abstract

Monitoring housing rental prices based on social media:An integrated approach of machine-learning algorithms and hedonic modeling to inform equitable housing policies

Cited by 163 publications

References 108 publications

A Comparative Assessment of Machine-Learning Techniques for Land Use and Land Cover Classification of the Brazilian Tropical Savanna Using ALOS-2/PALSAR-2 Polarimetric Images

A Comparative Assessment of Machine-Learning Techniques for Land Use and Land Cover Classification of the Brazilian Tropical Savanna Using ALOS-2/PALSAR-2 Polarimetric Images

Measuring Impacts of Urban Environmental Elements on Housing Prices Based on Multisource Data—A Case Study of Shanghai, China

Online rental housing market representation and the digital reproduction of urban inequality

Contact Info

Product

Resources

About