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

Abstract

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.

Changing Characteristics of Chlorophyll a in the Context of Internal and External Factors: A Case Study of Dianchi Lake in China

“…Its purpose is to provide a method to determine the optimal weight coefficient and to describe the error information. It is based on the data of several measured sample points in the limited field of the sample points to be estimated, after considering the relationship among the shape, size and spatial position of the sample points, the spatial position relationship of the sample points to be estimated, and the structural information provided by the function of variation [40]. The linear unbiased optimal estimation is carried out for the value of the sample to be estimated.…”

The Research Development of Hedonic Price Model-Based Real Estate Appraisal in the Era of Big Data

“…Most of the real estate big data resources used today are provided via the internet, and many housing transaction platforms have reshaped the way people exchange information in housing economics [35]. Most researchers' real estate data sources have been transformed into well-known real estate information websites, such as China's Lianjia.com (accessed on 11 February 2022) [36], Craigslist in the United States [37], and Idealista in Spain [38]. In addition, big geographic data resources are an important data source for housing price research in the era of big data.…”

“…At the same time, applications related to evaluation are now increasing. Although there are researchers who have used DL to handle simple residential features, finding the performance of the DL model to be superior to other machine learning models [123], most use it to solve the difficulty of quantifying the feature information contained in data, such as image and text [37,42,58,[60][61][62]66,74,124] Boosting: The working mechanism here combines a series of weak learners into a strong learner by reducing the bias in supervised learning. In other words, each base learner pays more attention to the error of the previous base learner, and this strategy is used to serialize the base learner into a strong classifier by continuously forcing the next weak learner to make up for the previous error.…”

The Evaluation of Rental Amount of Religious Endowments by Using Geomatic Techniques and Machine Learning Algorithms Hilla/ Iraq

“…Nowadays, deep learning techniques showed a significant accuracy in the field of prediction. Zhou et al [14] developed an approach based on the integration of Convolutional Neural Network and spatial data to predict real estate rental values. The main limitation of deep learning methods is that they required big data.…”