Housing Price Prediction via Improved Machine Learning Techniques

Truong, Quang Dinh; Nguyen, Minh; Dang, Hy; Mei, Bo

doi:10.1016/j.procs.2020.06.111

Cited by 120 publications

(58 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While image classification is one of the most prominent predictive applications in urban geography, there are of course other important predictive questions that can be answered in the era of "big" data: small area estimation and interpolation for socioeconomic data (Singleton and Arribas-Bel 2019), spatial patterns in large, open, georeferenced municipal data sets such as crimes, "311" calls, and parking violations (Gao et al 2019), spatiotemporal patterns in disease outbreaks using georeferenced sentiment data from social media (e.g., Allen et al 2016), the spatial distribution of pollution (Walsh et al 2017), the prediction of housing prices and rents (Mu, Wu, and Zhang 2014;Fan, Cui, and Zhong 2018;Phan 2018;Truong et al 2020), and gentrification (Alejandro and Palafox 2019; Knorr 2019), among others. In an urban planning context, predicting the future distribution of population and land use with greater precision is an area of significant opportunity for predictive model applications (Feng et al 2018).…”

Section: Literaturementioning

confidence: 99%

Spatial Models or Random Forest? Evaluating the Use of Spatially Explicit Machine Learning Methods to Predict Employment Density around New Transit Stations in Los Angeles

Credit

2021

Geographical Analysis

View full text Add to dashboard Cite

The increasing use of "new" machine learning techniques, such as random forest, provides an impetus to researchers to better understand the role of space in these models. Thus, this article develops an approach for constructing spatially explicit random forest models by including spatially lagged variables to mirror various spatial econometric specifications in order to test their comparative performance against traditional spatial and nonspatial regression models for predicting block-level employment density around new transit stations in Los Angeles. This article employs a "post hoc" testing approach to isolate the impact of a particular variable (transit proximity)-and supplemental diagnostics (such as partial dependence plots and permutation importances)-to help inform explanatory relationships. The results indicate that random forest models slightly outperform spatial econometric models, and the inclusion of spatial lag parameters modestly improves random forest model accuracy-the best-fit spatial random forest model demonstrates 84.61% accuracy in predicting post-construction employment density around newly built transit stations, compared to 81.88% for the best-fit spatial econometric model and 84.37% for the nonspatial random forest model. However, given these somewhat small differences, it is not possible to conclude that the random forest approach is clearly superior to traditional spatial econometric models from these results alone.

show abstract

Section: Literaturementioning

confidence: 99%

Spatial Models or Random Forest? Evaluating the Use of Spatially Explicit Machine Learning Methods to Predict Employment Density around New Transit Stations in Los Angeles

Credit

2021

Geographical Analysis

View full text Add to dashboard Cite

show abstract

“…The authors examine composite pre processing and feature engineering methodology by considering only .limited features and dataset. A hybrid Gradient boost regression and Lasso model had been proposed to predict the price of single house [8,10].…”

Section: Related Workmentioning

confidence: 99%

Prediction of House Price Using XGBoost Regression Algorithm

Avanija¹

2021

TURCOMAT

View full text Add to dashboard Cite

House price fluctuates each and every year due to changes in land value and change in infrastructure in and around the area. Centralised system should be available for prediction of house price in correlation with neighbourhood and infrastructure, will help customer to estimate the price of the house. Also, it assists the customer to come to a conclusion where to buy a house and when to purchase the house. Different factors are taken into consideration while predicting the worth of the house like location, neighbourhood and various amenities like garage space etc. Developing a model starts with Pre-processing data to remove all sort of discrepancies and fill null values or remove data outliers and make data ready to be processed. The categorical attribute can be converted into required attributes using one hot encoding methodology. Later the house price is predicted using XGBoost regression technique.

show abstract

“…One of the most widely used models in the real-estate field is the regression analysis namely the multiple linear regression, support vector regression, and hedonic regression analysis, which is used by several researchers including [9], [16]- [20]. In addition, several other machine learning models such as the gradient boosting model including Catboost, XGBoost and LightGBM, random forest, decision and artificial neural network have been used frequently in the study of real-estate [10], [11], [21]- [23]. In this study, four models namely multiple regression analysis, ridge regression, LightGBM, and XGBoost are used to learn about the relationship between house attributes and house prices as well as to predict house prices.…”

Section: B Housing Price Prediction Modelsmentioning

confidence: 99%

Advanced Machine Learning Algorithms for House Price Prediction: Case Study in Kuala Lumpur

Abdul-Rahman¹,

Zulkifley²,

Ibrahim³

et al. 2021

IJACSA

View full text Add to dashboard Cite

House price is affected significantly by several factors and determining a reasonable house price involves a calculative process. This paper proposes advanced machine learning (ML) approaches for house price prediction. Two recent advanced ML algorithms, namely LightGBM and XGBoost were compared with two traditional approaches: multiple regression analysis and ridge regression. This study utilizes a secondary dataset called 'Property Listing in Kuala Lumpur', gathered from Kaggle and Google Map, containing 21984 observations with 11 variables, including a target variable. The performance of the ML models was evaluated using mean absolute error (MAE), root mean square error (RMSE), and adjusted r-squared value. The findings revealed that the house price prediction model based on XGBoost showed the highest performance by generating the lowest MAE and RMSE, and the closest adjusted r-squared value to one, consistently outperformed other ML models. A new dataset which consists of 1300 samples was deployed at the model deployment stage. It was found that the percentage of the variance between the actual and predicted price was relatively small, which indicated that this model is reliable and acceptable. This study can greatly assist in predicting future house prices and the establishment of real estate policies.

show abstract

Housing Price Prediction via Improved Machine Learning Techniques

Cited by 120 publications

References 6 publications

Spatial Models or Random Forest? Evaluating the Use of Spatially Explicit Machine Learning Methods to Predict Employment Density around New Transit Stations in Los Angeles

Spatial Models or Random Forest? Evaluating the Use of Spatially Explicit Machine Learning Methods to Predict Employment Density around New Transit Stations in Los Angeles

Prediction of House Price Using XGBoost Regression Algorithm

Advanced Machine Learning Algorithms for House Price Prediction: Case Study in Kuala Lumpur

Contact Info

Product

Resources

About