Regression model for appraisal of real estate using recurrent neural network and boosting tree

Bin, Junchi; Tang, Shiyuan; Liu, Yihao; Wang, Gang; Gardiner, Bryan; Liu, Zheng; Li, Eric

doi:10.1109/ciapp.2017.8167209

Cited by 25 publications

(16 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, various machine learning and deep learning algorithms, such as Random Forest [17], Support Vector Machines (SVM) [18], and Long Short-Term Memory (LSTM) [19], have been used to predict real estate prices showing that the performance of real estate valuation can be improved by extending the predictor set to include mortgage contract rate [8], features extracted from home interiors and exteriors [20], or satellite images [21,22]. While some prior work focused on the estimation of the single property price, others applied the methods to predicting the trend of the real estate price index such as Zillow Home Value Index (ZHVI) [9].…”

Section: Housing Price Estimationmentioning

confidence: 99%

“…Among various ensemble methods, boosting-based methods are designed to reduce bias and variance by utilizing sequential learners. Prior research [19] found a boosting model to be superior with a higher estimation accuracy than a traditional hedonic model (regression model). Further, gradient boosting tree-based (GBT) methods are known to be more accurate than bootstrap aggregating (bagging) methods such as Random Forest for difficult cases [23,24].…”

Section: Price Estimation Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Applying Comparable Sales Method to the Automated Estimation of Real Estate Prices

Kim¹,

Choi

2020

Sustainability

View full text Add to dashboard Cite

In this paper, we propose a novel procedure designed to apply comparable sales method to the automated price estimation of real estates, in particular, that of apartments. Apartments are the most popular residential housing type in Korea. The price of a single apartment is influenced by many factors, making it hard to estimate accurately. Moreover, as an apartment is purchased for living, with a sizable amount of money, it is mostly traded infrequently. Thus, its past transaction price may not be particularly helpful to the estimation after a certain period of time. For these reasons, the up-to-date price of an apartment is commonly estimated by certified appraisers, who typically rely on comparable sales method (CSM). CSM requires comparable properties to be identified and used as references in estimating the current price of the property in question. In this research, we develop a procedure to systematically apply this procedure to the automated estimation of apartment prices and assess its applicability using nine years’ real transaction data from the capital city and the most-populated province in South Korea and multiple scenarios designed to reflect the conditions of low and high fluctuations of housing prices. The results from extensive evaluations show that the proposed approach is superior to the traditional approach of relying on real estate professionals and also to the baseline machine learning approach.

show abstract

Section: Housing Price Estimationmentioning

confidence: 99%

Section: Price Estimation Modelsmentioning

confidence: 99%

Applying Comparable Sales Method to the Automated Estimation of Real Estate Prices

Kim¹,

Choi

2020

Sustainability

View full text Add to dashboard Cite

show abstract

“…Traditional valuation methods are handicapped in estimation of property value arising from huge (big) data that captures the location, socioeconomic, physical, environmental and demographic characteristics of real estate [43][44]. ANN has shown to be very keen on tackling the problem [45]. The advantage of ANN over the traditional evaluation tools is that the learning function [46] and nonlinear processing ability of ANN can improve the randomness and uncertainty of existing evaluation methods thereby minimizing the likelihood of information loss [47].…”

Section: Evaluation Modelsmentioning

confidence: 99%

Review on the Application of Artificial Neural Networks in Real Estate Valuation

Nkolika¹

2020

IJATCSE

View full text Add to dashboard Cite

Real estate appraisal is needed in assessment of the value of properties and contribute the regional economy of any country. Real estate valuation is thus an important subject, which has to be studied carefully as there are many individual subjective criteria, which often results in variations, which makes the traditional valuation methods to be inadequate. This work aimed at coping with the complexity of real estate valuation, by putting forth the advantages of artificial neural network, one of the novel model of real estate appraisal. The review of literature has helped to establish that the neural network model is better than the traditional model previously. This work opens up a new and better understanding to the principle of real estate evaluation.

show abstract

“…The stability of these attributes was then studied, in order to explore their sensitivity to changes in the sample. This analysis was carried out due to the need in machine learning approaches to find the most stable-important attributes in order to predict the phenomenon under study with the minimum possible redundancy, which favors parsimony and inferential interpretation of the model [8,19,20]. We then proceeded with the interpretation of the results, supported by metrics of variability/error/impurity reduction according to the method with which the chosen model was trained.…”

Section: Important Attributes Stability Analysis and Interpretationmentioning

confidence: 99%

Modeling of apartment prices in a Colombian context from a machine learning approach with stable-important attributes

Rave

Echavarría

Correa

2020

DYNA

View full text Add to dashboard Cite

The objective of this work is to develop a machine learning model for online pricing of apartments in a Colombian context. This article addresses three aspects: i) it compares the predictive capacity of linear regression, regression trees, random forest and bagging; ii) it studies the effect of a group of text attributes on the predictive capability of the models; and iii) it identifies the more stable-important attributes and interprets them from an inferential perspective to better understand the object of study. The sample consists of 15,177 observations of real estate. The methods of assembly (random forest and bagging) show predictive superiority with respect to others. The attributes derived from the text had a significant relationship with the property price (on a log scale). However, their contribution to the predictive capacity was almost nil, since four different attributes achieved highly accurate predictions and remained stable when the sample change.

show abstract

Regression model for appraisal of real estate using recurrent neural network and boosting tree

Cited by 25 publications

References 4 publications

Applying Comparable Sales Method to the Automated Estimation of Real Estate Prices

Applying Comparable Sales Method to the Automated Estimation of Real Estate Prices

Review on the Application of Artificial Neural Networks in Real Estate Valuation

Modeling of apartment prices in a Colombian context from a machine learning approach with stable-important attributes

Contact Info

Product

Resources

About