Boosted Tree Ensembles for Artificial Intelligence Based Automated Valuation Models (AI-AVM)

Sing, Tien Foo; Yang, Jesse Jingye; Yu, Shi Ming

doi:10.1007/s11146-021-09861-1

Cited by 18 publications

(13 citation statements)

References 46 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Support vector machine technique was adopted to forecast residential housing price in Taipei city by Chen et al (2017) and Lee and Chen (2016). Sing et al (2022) recently employed the boosting tree ensemble technique to predict the price of real estate in Singapore. For more information on MLbased mass appraisal real estate models, please refer to the review paper by Wang and Li (2019).…”

Section: Non-parametric Machine Learning (Ml) Methods and Combined Ap...mentioning

confidence: 99%

Combination of Machine Learning-Based Automatic Valuation Models for Residential Properties in South Korea

Hong

Kim

2022

International Journal of Strategic Property Management

View full text Add to dashboard Cite

The applicability of machine learning (ML) techniques has recently been expanding to include automatic real estate valuation models. The main advantage of this technique is that it can better capture complexity in the value determination process. Therefore, the performance of these techniques is shown to be superior to conventional models. In this paper, the latest ML algorithms (i.e., support vector machine, random forest, XGBoost, LightGBM, and CatBoost algorithms) are examined as automatic valuation models, and several combination methods are proposed to improve the models’ predictive power. We applied ML models to approximately 57,000 records on apartment transactions, which were provided by South Korea’s Ministry of Land, Infrastructure, and Transport, that occurred in Seoul in 2018. The results are as follows. First, ML-based predictors (especially, the latest decision tree-based algorithms) are more performative than conventional models. Second, the prediction error from a model can be partially offset by another model’s error, which implies that an efficient averaging of the predictors improves their predictive accuracy. Third, the models’ relative performance may be relearned by the ML algorithms, which means that they can also be used to recommend which algorithm should be selected for making predictions.

show abstract

Section: Non-parametric Machine Learning (Ml) Methods and Combined Ap...mentioning

confidence: 99%

Combination of Machine Learning-Based Automatic Valuation Models for Residential Properties in South Korea

Hong

Kim

2022

International Journal of Strategic Property Management

View full text Add to dashboard Cite

show abstract

“…It is also seen to have a ±10% error margin (Jian-Jiun et al, 2012). Other data mining related models include support vector machine, elastic net, XGBoost, Light Gradient Boosting Machine (LGBM), random forest, kernel ridge, lasso and gradient boost (Dey and Urolagin, 2021); extra trees regression (Hu et al, 2019); decision tree (Sing et al, 2021) and K-nearest neighbour (Pow et al, 2014).…”

Section: Literature Review 21 Modelling Techniques In Real Estate Pri...mentioning

confidence: 99%

An analysis of the determinants of office real estate price modelling in Nigeria: using a Delphi approach

Yakub

Achu

Ali

et al. 2022

View full text Add to dashboard Cite

PurposeThere are a plethora of putative influencing variables available in the literature for modelling real estate prices using AI. Their choice tends to differ from one researcher to the other, consequently leading to subjectivity in the selection process. Thus, there is a need to seek the viewpoint of practitioners on the applicability and level of significance of these academically established variables.Design/methodology/approachUsing the Delphi technique, this study collated and structured the 35 underlying micro- and macroeconomic parameters derived from literature and eight variables suggested by 11 selected real estate experts. The experts ranked these variables in order of influence using a seven-point Likert scale with a reasonable consensus during the fourth round (Kendall's W = 0.7418).FindingsThe study discovered that 16 variables are very influential with seven being extremely influential. These extremely influential variables include flexibility, adaptability of design, accessibility to the building, the size of office spaces, quality of construction, state of repairs, expected capital growth and proximity to volatile areas.Practical implicationsThe results of this study improve the quality of data available to valuers towards a fortified price prediction for investors, and thereby, restoring the valuers' credibility and integrity.Originality/valueThe “volatility level of an area”, which was revealed as a distinct factor in the survey is used to add to current knowledge concerning office price. Hence, this study offers real estate practitioners and researchers valuable knowledge on the critical variables that must be considered in AI-based price modelling.

show abstract

“…Spatial methods were categorized into SAR (spatial autoregressive) models, local models (e.g., geographically weighted regression) and geostatistical models (e.g., kriging). AVMs (automated valuation models) were discussed in (d'Amato, 2017) and (Sing et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Might expert knowledge improve econometric real estate mass appraisal?

Doszyń

2022

J Real Estate Finan Econ

View full text Add to dashboard Cite

The article examines whether expert knowledge improves the estimation results of real estate mass appraisal models. Six econometric models were compared: OLS, mixed, the Bayesian model, the Inequality Restricted Least Squares (IRLS) model, ridge and LASSO regression (with regularization). In three of the models (mixed, Bayesian, and IRLS) prior knowledge was applied. In mixed and Bayesian models priors took the form of intervals for model parameters. In IRLS, restrictions in the form of inequalities were applied. In the empirical example mass appraisal models were applied in the valuation of undeveloped land for residential purposes. Models with prior knowledge turned out to be the best with regard to the consistency of estimates with theory. Also, prediction accuracy was better for models with prior knowledge. In the case of low quality data expert knowledge might significantly improve estimation results of real estate mass appraisal econometric models.

show abstract

Boosted Tree Ensembles for Artificial Intelligence Based Automated Valuation Models (AI-AVM)

Cited by 18 publications

References 46 publications

Combination of Machine Learning-Based Automatic Valuation Models for Residential Properties in South Korea

Combination of Machine Learning-Based Automatic Valuation Models for Residential Properties in South Korea

An analysis of the determinants of office real estate price modelling in Nigeria: using a Delphi approach

Might expert knowledge improve econometric real estate mass appraisal?

Contact Info

Product

Resources

About