Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market

Michael Sahl Lystbæk; Tharsika Pakeerathan Srirajan

doi:10.1007/978-3-031-62495-7_40

Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market

Michael Sahl Lystbæk^*, Tharsika Pakeerathan Srirajan

^*Corresponding author for this work

Department of Business Development and Technology

Research output: Contribution to book/anthology/report/proceeding › Article in proceedings › Research › peer-review

Abstract

The housing market is impacted by a variety of parameters which gives a complexity that is difficult to analyze with traditional statistical approaches due to the large number of interdependent variables that the market data provides. In this study, ML techniques are utilized to provide a deeper understanding of the Danish housing market based on a dataset of sales cases provided by a leading Danish real estate agency. We propose an extreme gradient boosting model for sales price regression, and we propose using feature importance techniques to provide insight into important parameters in the national housing market. The regression model trained for sales price with grid search cross-validation for parameter optimization achieves an R² accuracy of 0.84, an MAE of DKK 433,824, and an RMSE of DKK 675,817. Permutation-based feature importance defines the most impactful parameters for the sales price regression where the four features with the highest impacts are: 1. GisX (West/East location), 2. GisY (North/South location), 3. Building area, 4. Construction year. The results for geographical distribution regarding price, building area, and plot area are illustrated with 2D partial dependence plots of geographical distributions to enhance the understanding of market trends.

Original language	English
Title of host publication	Engineering Applications of Neural Networks : 25th International Conference, EANN 2024, Corfu, Greece, June 27–30, 2024, Proceedings
Editors	Lazaros Iliadis, Ilias Maglogiannis, Antonios Papaleonidas, Elias Pimenidis, Chrisina Jayne
Number of pages	14
Publisher	Springer Science and Business Media Deutschland GmbH
Publication date	2024
Pages	530-543
ISBN (Print)	978-3-031-62494-0
ISBN (Electronic)	978-3-031-62495-7
DOIs	https://doi.org/10.1007/978-3-031-62495-7_40
Publication status	Published - 2024
Event	25th International Conference on Engineering Applications of Neural Networks, EANN 2024 - Corfu, Greece Duration: 27 Jun 2024 → 30 Jun 2024

Conference

Conference	25th International Conference on Engineering Applications of Neural Networks, EANN 2024
Country/Territory	Greece
City	Corfu
Period	27/06/2024 → 30/06/2024

Series	Communications in Computer and Information Science
Volume	2141 CCIS
ISSN	1865-0929

Keywords

Feature Importance
Gradient Boosting Regression
Housing Market Pricing
Machine Learning
Partial Dependence

Access to Document

10.1007/978-3-031-62495-7_40

Cite this

Lystbæk, M. S., & Srirajan, T. P. (2024). Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market. In L. Iliadis, I. Maglogiannis, A. Papaleonidas, E. Pimenidis, & C. Jayne (Eds.), Engineering Applications of Neural Networks: 25th International Conference, EANN 2024, Corfu, Greece, June 27–30, 2024, Proceedings (pp. 530-543). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-62495-7_40

Lystbæk, Michael Sahl ; Srirajan, Tharsika Pakeerathan. / Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market. Engineering Applications of Neural Networks: 25th International Conference, EANN 2024, Corfu, Greece, June 27–30, 2024, Proceedings. editor / Lazaros Iliadis ; Ilias Maglogiannis ; Antonios Papaleonidas ; Elias Pimenidis ; Chrisina Jayne. Springer Science and Business Media Deutschland GmbH, 2024. pp. 530-543 (Communications in Computer and Information Science, Vol. 2141 CCIS).

@inproceedings{05b75d1e5a43477ab81609eacbffcb27,

title = "Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market",

abstract = "The housing market is impacted by a variety of parameters which gives a complexity that is difficult to analyze with traditional statistical approaches due to the large number of interdependent variables that the market data provides. In this study, ML techniques are utilized to provide a deeper understanding of the Danish housing market based on a dataset of sales cases provided by a leading Danish real estate agency. We propose an extreme gradient boosting model for sales price regression, and we propose using feature importance techniques to provide insight into important parameters in the national housing market. The regression model trained for sales price with grid search cross-validation for parameter optimization achieves an R2 accuracy of 0.84, an MAE of DKK 433,824, and an RMSE of DKK 675,817. Permutation-based feature importance defines the most impactful parameters for the sales price regression where the four features with the highest impacts are: 1. GisX (West/East location), 2. GisY (North/South location), 3. Building area, 4. Construction year. The results for geographical distribution regarding price, building area, and plot area are illustrated with 2D partial dependence plots of geographical distributions to enhance the understanding of market trends.",

keywords = "Feature Importance, Gradient Boosting Regression, Housing Market Pricing, Machine Learning, Partial Dependence",

author = "Lystb{\ae}k, {Michael Sahl} and Srirajan, {Tharsika Pakeerathan}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; 25th International Conference on Engineering Applications of Neural Networks, EANN 2024 ; Conference date: 27-06-2024 Through 30-06-2024",

year = "2024",

doi = "10.1007/978-3-031-62495-7_40",

language = "English",

isbn = "978-3-031-62494-0",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "530--543",

editor = "Lazaros Iliadis and Ilias Maglogiannis and Antonios Papaleonidas and Elias Pimenidis and Chrisina Jayne",

booktitle = "Engineering Applications of Neural Networks",

address = "Germany",

}

Lystbæk, MS & Srirajan, TP 2024, Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market. in L Iliadis, I Maglogiannis, A Papaleonidas, E Pimenidis & C Jayne (eds), Engineering Applications of Neural Networks: 25th International Conference, EANN 2024, Corfu, Greece, June 27–30, 2024, Proceedings. Springer Science and Business Media Deutschland GmbH, Communications in Computer and Information Science, vol. 2141 CCIS, pp. 530-543, 25th International Conference on Engineering Applications of Neural Networks, EANN 2024, Corfu, Greece, 27/06/2024. https://doi.org/10.1007/978-3-031-62495-7_40

Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market. / Lystbæk, Michael Sahl ; Srirajan, Tharsika Pakeerathan.
Engineering Applications of Neural Networks: 25th International Conference, EANN 2024, Corfu, Greece, June 27–30, 2024, Proceedings. ed. / Lazaros Iliadis; Ilias Maglogiannis; Antonios Papaleonidas; Elias Pimenidis; Chrisina Jayne. Springer Science and Business Media Deutschland GmbH, 2024. p. 530-543 (Communications in Computer and Information Science, Vol. 2141 CCIS).

Research output: Contribution to book/anthology/report/proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market

AU - Lystbæk, Michael Sahl

AU - Srirajan, Tharsika Pakeerathan

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024

Y1 - 2024

N2 - The housing market is impacted by a variety of parameters which gives a complexity that is difficult to analyze with traditional statistical approaches due to the large number of interdependent variables that the market data provides. In this study, ML techniques are utilized to provide a deeper understanding of the Danish housing market based on a dataset of sales cases provided by a leading Danish real estate agency. We propose an extreme gradient boosting model for sales price regression, and we propose using feature importance techniques to provide insight into important parameters in the national housing market. The regression model trained for sales price with grid search cross-validation for parameter optimization achieves an R2 accuracy of 0.84, an MAE of DKK 433,824, and an RMSE of DKK 675,817. Permutation-based feature importance defines the most impactful parameters for the sales price regression where the four features with the highest impacts are: 1. GisX (West/East location), 2. GisY (North/South location), 3. Building area, 4. Construction year. The results for geographical distribution regarding price, building area, and plot area are illustrated with 2D partial dependence plots of geographical distributions to enhance the understanding of market trends.

AB - The housing market is impacted by a variety of parameters which gives a complexity that is difficult to analyze with traditional statistical approaches due to the large number of interdependent variables that the market data provides. In this study, ML techniques are utilized to provide a deeper understanding of the Danish housing market based on a dataset of sales cases provided by a leading Danish real estate agency. We propose an extreme gradient boosting model for sales price regression, and we propose using feature importance techniques to provide insight into important parameters in the national housing market. The regression model trained for sales price with grid search cross-validation for parameter optimization achieves an R2 accuracy of 0.84, an MAE of DKK 433,824, and an RMSE of DKK 675,817. Permutation-based feature importance defines the most impactful parameters for the sales price regression where the four features with the highest impacts are: 1. GisX (West/East location), 2. GisY (North/South location), 3. Building area, 4. Construction year. The results for geographical distribution regarding price, building area, and plot area are illustrated with 2D partial dependence plots of geographical distributions to enhance the understanding of market trends.

KW - Feature Importance

KW - Gradient Boosting Regression

KW - Housing Market Pricing

KW - Machine Learning

KW - Partial Dependence

UR - http://www.scopus.com/inward/record.url?scp=85198979257&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-62495-7_40

DO - 10.1007/978-3-031-62495-7_40

M3 - Article in proceedings

AN - SCOPUS:85198979257

SN - 978-3-031-62494-0

T3 - Communications in Computer and Information Science

SP - 530

EP - 543

BT - Engineering Applications of Neural Networks

A2 - Iliadis, Lazaros

A2 - Maglogiannis, Ilias

A2 - Papaleonidas, Antonios

A2 - Pimenidis, Elias

A2 - Jayne, Chrisina

PB - Springer Science and Business Media Deutschland GmbH

T2 - 25th International Conference on Engineering Applications of Neural Networks, EANN 2024

Y2 - 27 June 2024 through 30 June 2024

ER -

Lystbæk MS , Srirajan TP. Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market. In Iliadis L, Maglogiannis I, Papaleonidas A, Pimenidis E, Jayne C, editors, Engineering Applications of Neural Networks: 25th International Conference, EANN 2024, Corfu, Greece, June 27–30, 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2024. p. 530-543. (Communications in Computer and Information Science, Vol. 2141 CCIS). doi: 10.1007/978-3-031-62495-7_40

Machine Learning-Based Feature Mapping for Enhanced Understanding of the Housing Market

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this