New Insights into Rental Housing Markets across the United States: Web Scraping and Analyzing Craigslist Rental Listings

Boeing, Geoff; Waddell, Paul

doi:10.1177/0739456x16664789

Cited by 122 publications

(93 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The mean number of listings per square kilometer or neighborhoods in Wards 7 and 8 is 0.0063 (median 0.0054, SD 0.0035), whereas the rest of the neighborhoods showed a mean of 0.0526 (median 0.0352, SD 0.0539), suggesting that the lack of n-gram neighborhood identification was due to the lack of listings, not necessarily missing names in the text or false negatives. This bias in rental listings related to poverty supports existing research in this area [61].…”

Section: Listing Regional Bias and False Negativessupporting

confidence: 79%

Identifying Urban Neighborhood Names through User-Contributed Online Property Listings

McKenzie

Liu

et al. 2018

IJGI

View full text Add to dashboard Cite

Neighborhoods are vaguely defined, localized regions that share similar characteristics. They are most often defined, delineated and named by the citizens that inhabit them rather than municipal government or commercial agencies. The names of these neighborhoods play an important role as a basis for community and sociodemographic identity, geographic communication and historical context. In this work, we take a data-driven approach to identifying neighborhood names based on the geospatial properties of user-contributed rental listings. Through a random forest ensemble learning model applied to a set of spatial statistics for all n-grams in listing descriptions, we show that neighborhood names can be uniquely identified within urban settings. We train a model based on data from Washington, DC, and test it on listings in Seattle, WA, and Montréal, QC. The results indicate that a model trained on housing data from one city can successfully identify neighborhood names in another. In addition, our approach identifies less common neighborhood names and suggestions of alternative or potentially new names in each city. These findings represent a first step in the process of urban neighborhood identification and delineation.

show abstract

Section: Listing Regional Bias and False Negativessupporting

confidence: 79%

Identifying Urban Neighborhood Names through User-Contributed Online Property Listings

McKenzie

Liu

et al. 2018

IJGI

View full text Add to dashboard Cite

show abstract

“…In recent years, Craigslist data have become important sources for urban studies. As pointed out in Boeing and Waddell (2017), a researcher can scrape publicly available data such as Craigslist listings for non-commercial uses that neither repackage nor relist the data [1]. Accordingly, they used nationwide Craigslist rental housing lists to analyze rental housing markets across the US.…”

Section: Datamentioning

confidence: 99%

“…The rental housing market is a very important real estate market in the United States. Renter-occupied housing accounted for 35 percent of all US households in 2012, and a total of 43 million households by 2013 [1,2]. Based on information from Zillow, the total rent in the US has increased over recent years, reaching a record high of $485.6 billion in 2017 [3].…”

Section: Introductionmentioning

confidence: 99%

Modeling Housing Rent in the Atlanta Metropolitan Area Using Textual Information and Deep Learning

Zhou

Tong

2019

IJGI

View full text Add to dashboard Cite

The rental housing market plays a critical role in the United States real estate market. In addition, rent changes are also indicators of urban transformation and social phenomena. However, traditional data sources for market rent prediction are often inaccurate or inadequate at covering large geographies. With the development of housing information exchange platforms such as Craigslist, user-generated rental listings now provide big data that cover wide geographies and are rich in textual information. Given the importance of rent prediction in urban studies, this study aims to develop and evaluate models of rental market dynamics using deep learning approaches on spatial and textual data from Craigslist rental listings. We tested a number of machine learning and deep learning models (e.g., convolutional neural network, recurrent neural network) for the prediction of rental prices based on data collected from Atlanta, GA, USA. With textual information alone, deep learning models achieved an average root mean square error (RMSE) of 288.4 and mean absolute error (MAE) of 196.8. When combining textual information with location and housing attributes, the integrated model achieved an average RMSE of 227.9 and MAE of 145.4. These approaches can be applied to assess the market value of rental properties, and the prediction results can be used as indicators of a variety of urban phenomena and provide practical references for home owners and renters.

show abstract

“…Web scraping is a technique to extract structured data set from the websites and provide human-readable content. A web scraper can extract important elements of the web page which is saved in a structured data set [13]. Therefore, the user's search information such as category, subcategory and products price are obtained with this technique and stored in the PostgreSQL database.…”

Section: Figure 1-a Piece Of the Raw Data Acquired From The Companymentioning

confidence: 99%

Discover Points of Interest Based on Users’ Internet Searches Through an Online Shopping Website

Shahriari-Mehr

Delavar

Claramunt

et al. 2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In recent years, the development of the Internet plays a significant role in human's daily activities. One of the most important effects of the Internet is the change in the process of shopping. The advent of online shopping leads to establish a new channel for customers to obtain information about their desired goods and demands. Although many customers collect information from online channel, they also wish to try and search for their required goods at the stores. Besides, discovering this data leads to a new source for spatial analysis to find the users’ interests. Therefore, we can consider this data as a contextual information source for spatial analysis or primary source for recommending points of interest (POIs). In this research, our aim is to discover a relation among the users' internet searches and the goods at the stores to recommend the best store to the users. Euclidean distance is used to calculate the similarity between users' searches and the available goods at the stores. The proposed method has been implemented in the city of Tehran, capital of Iran. The results show that the users’ internet search behavior plays an essential role in the recommendation system which provides stores to the users based on the similarity among the users’ internet searches and the available goods at the stores.

show abstract

New Insights into Rental Housing Markets across the United States: Web Scraping and Analyzing Craigslist Rental Listings

Cited by 122 publications

References 49 publications

Identifying Urban Neighborhood Names through User-Contributed Online Property Listings

Identifying Urban Neighborhood Names through User-Contributed Online Property Listings

Modeling Housing Rent in the Atlanta Metropolitan Area Using Textual Information and Deep Learning

Discover Points of Interest Based on Users’ Internet Searches Through an Online Shopping Website

Contact Info

Product

Resources

About