A machine learning approach to big data regression analysis of real estate prices for inferential and predictive purposes

Rave, Jorge Iván Pérez; Correa, Juan Carlos; Echavarría, Favián González

doi:10.1080/09599916.2019.1587489

Cited by 66 publications

(54 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In line with the study by Pérez-Rave et al [20], we carry out the estimation and measurement of errors using monetary values since any transformation of the variable to be estimated (price), such as the logarithmic transformation, can lead to an improvement in results from a fictitious statistical point of view. In addition, the estimated value of the price is made in monetary terms and does not require any transformation for its interpretation and comparison between locations.…”

Section: Methodsologymentioning

confidence: 99%

“…To do this, a CART algorithm is applied, using the percentage error (estimated value less real value in absolute value divided by real value) as a dependent variable and the sales ratio (estimated value divided by real value) to determine segments of observations that allow them to go from a general MAPE in the simple training of 12,688 to a value in the best segment of 9,783 and in the simple test of 14,859 to 12,364. Pérez-Rave et al [20] propose a methodology that incorporates a variable selection procedure called simple incremental with resampling (MIN-REM).…”

Section: Literature Reviewmentioning

confidence: 99%

“…In addition, the data are quite varied and the sale value on the web and the offline sale value are seen to be of similar magnitude. e Internet source also offers information on a variety of property and neighbourhood characteristics that are difficult to find from other sources [20]. However, this source of information has been little used despite the existence of applications developed with great success in both the real estate sector as well as other sectors [54].…”

Section: Empirical Applicationmentioning

confidence: 99%

“…Although these techniques were initially used more as classification methods, in recent years, their application has been used in determining the most influential variables on house pricing and in estimating dwelling prices. Pérez-Rave et al [20] provide a two-stage methodology for the analysis of big data regression under a machine learning approach for both inferential and predictive purposes.…”

Section: Introductionmentioning

confidence: 99%

“…Research has been carried out by Jaen [12] in Coral Gables (Florida, USA); Fan et al [13] in Singapore (Republic of Singapore);Özsoy and Şahin [23] in Istanbul (Turkey); Del Cacho [14] in Madrid (Spain); Pow et al [17] in Montreal (Canada); Ceh et al [24] in Ljubljana, (Slovenia); Nguyen [25] in 5 counties of USA; and Dimopoulos et al [26] in Nicosia (Cyprus). In contrast, Pérez-Rave et al [20] deal with the estimation of dwelling prices for a whole country, Colombia, using independent variables identifying the city in which each property is located, thus proposing a unique model for the entire country (with a sample of 61,826 properties).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Fully Automated Adjustment of Ensemble Methods in Machine Learning for Modeling Complex Real Estate Systems

et al. 2020

View full text Add to dashboard Cite

The close relationship between collateral value and bank stability has led to a considerable need to a rapid and economical appraisal of real estate. The greater availability of information related to housing stock has prompted to the use of so-called big data and machine learning in the estimation of property prices. Although this methodology has already been applied to the real estate market to identify which variables influence dwelling prices, its use for estimating the price of properties is not so frequent. The application of this methodology has become more sophisticated over time, from applying simple methods to using the so-called ensemble methods and, while the estimation capacity has improved, it has only been applied to specific geographical areas. The main contribution of this article lies in developing an application for the entire Spanish market that fully automatically provides the best model for each municipality. Real estate property prices in 433 municipalities are estimated from a sample of 790,631 dwellings, using different ensemble methods based on decision trees such as bagging, boosting, and random forest. The results for estimating the price of dwellings show a good performance of the techniques developed, in terms of the error measures, with the best results being achieved using the techniques of bagging and random forest.

show abstract

Section: Methodsologymentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Empirical Applicationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Fully Automated Adjustment of Ensemble Methods in Machine Learning for Modeling Complex Real Estate Systems

et al. 2020

View full text Add to dashboard Cite

show abstract

Advertising through UAVs: Optimized path system for delivering smart real‐estate advertisement materials

Ullah

Al‐Turjman²,

Qayyum

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Real-estate advertisements through electronic and print media are bringing considerable fortune to the global real-estate sector. However, innovative advertisement methods must be adopted if real estate aims to transform into smart real estate. The current study, which is based on a systematic literature review of 58 articles published in the last decade, identifies key media for real-estate advertisements as print media (e.g., magazines, brochures, newspapers, and digests), electronic media (e.g., websites, social media, and other digital tools), and mixed methods (e.g., billboards, signs and banners, and personalized messaging). This study takes the case of Kingsford suburb in the eastern Sydney area, and investigates the performance of the Australian real-estate industry in general and lists the key dynamics of properties in Kingsford and its prominent real-estate agencies. An unmanned aerial vehicle (UAV)-based smart real-estate advertisement material delivery system is proposed to deliver advertisement materials and gifts to the potential customers of these agencies. The system paths are optimized through four Java-run algorithms: greedy, interroute, intraroute, and Tabu. Results based on six cases, three each for rent and sales with varying numbers of customers and UAVs and an 8-h operating time, indicate that the Tabu algorithm provides the best-optimized paths in all cases, followed by the interroute, intraroute, and greedy algorithms. However, the inter-and intraroute algorithms show superior performance in terms of computation speed. The proposed framework is a practical approach in disrupting the real-estate advertising sector, thereby helping this sector transform into a smart real estate consistent with industry 4.0 goals.

show abstract

Sustainable development scale of housing estates: An economic assessment using machine learning approach

Tang

Wong

2021

Sustainable Development

View full text Add to dashboard Cite

Economic sustainability is often addressed from the perspective of economic growth and at the national level. In contrast, this research attempts to examine the question of economic sustainability of human settlement at a local project level. Urban planners need to strike a balance between dispersal and over-concentration of population in cities. The existing theories suggest that either excessively low or extremely high

show abstract

A machine learning approach to big data regression analysis of real estate prices for inferential and predictive purposes

Cited by 66 publications

References 23 publications

A Fully Automated Adjustment of Ensemble Methods in Machine Learning for Modeling Complex Real Estate Systems

A Fully Automated Adjustment of Ensemble Methods in Machine Learning for Modeling Complex Real Estate Systems

Advertising through UAVs: Optimized path system for delivering smart real‐estate advertisement materials

Sustainable development scale of housing estates: An economic assessment using machine learning approach

Contact Info

Product

Resources

About