Comparing multilevel modelling and artificial neural networks in house price prediction

Yingyu Feng; Kelvyn Jones

doi:10.1109/ICSDM.2015.7298035

Comparing multilevel modelling and artificial neural networks in house price prediction

Yingyu Feng, Kelvyn Jones

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

22 Citations (Scopus)

336 Downloads (Pure)

Abstract

Two advanced modelling approaches, Multi-Level Models and Artificial Neural Networks are employed to model house prices. These approaches and the standard Hedonic Price Model are compared in terms of predictive accuracy, capability to capture location information, and their explanatory power. These models are applied to 2001-2013 house prices in the Greater Bristol area, using secondary data from the Land Registry, the Population Census and Neighbourhood Statistics so that these models could be applied nationally. The results indicate that MLM offers good predictive accuracy with high explanatory power, especially if neighbourhood effects are explored at multiple spatial scales.

Original language	English
Title of host publication	2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015)
Subtitle of host publication	Proceedings of a meeting held 8-10 July 2015, Fuzhou, China.
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	108-114
Number of pages	7
Volume	1
ISBN (Electronic)	9781479977482
ISBN (Print)	9781479977505
DOIs	https://doi.org/10.1109/ICSDM.2015.7298035
Publication status	Published - 8 Jul 2015
Event	Spatial Data Mining and Geographical Knowledge Services (ICSDM), 2015 2nd IEEE International Conference - Fuzhou, China Duration: 8 Jul 2015 → 10 Jul 2015

Conference

Conference	Spatial Data Mining and Geographical Knowledge Services (ICSDM), 2015 2nd IEEE International Conference
Country/Territory	China
City	Fuzhou
Period	8/07/15 → 10/07/15

Keywords

Artificial neural networks
House prices
Multilevel modelling
Predictive accuracy

Access to Document

10.1109/ICSDM.2015.7298035

ICSDM2015_submission_15_edited by flnAccepted author manuscript, 4.31 MB

Handle.net

Persistent link

Cite this

Feng, Y., & Jones, K. (2015). Comparing multilevel modelling and artificial neural networks in house price prediction. In 2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015): Proceedings of a meeting held 8-10 July 2015, Fuzhou, China. (Vol. 1, pp. 108-114). Article 15 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICSDM.2015.7298035

Feng, Yingyu ; Jones, Kelvyn. / Comparing multilevel modelling and artificial neural networks in house price prediction. 2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015): Proceedings of a meeting held 8-10 July 2015, Fuzhou, China.. Vol. 1 Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 108-114

@inproceedings{4cb022a6f18c4859819af562397648bc,

title = "Comparing multilevel modelling and artificial neural networks in house price prediction",

abstract = "Two advanced modelling approaches, Multi-Level Models and Artificial Neural Networks are employed to model house prices. These approaches and the standard Hedonic Price Model are compared in terms of predictive accuracy, capability to capture location information, and their explanatory power. These models are applied to 2001-2013 house prices in the Greater Bristol area, using secondary data from the Land Registry, the Population Census and Neighbourhood Statistics so that these models could be applied nationally. The results indicate that MLM offers good predictive accuracy with high explanatory power, especially if neighbourhood effects are explored at multiple spatial scales.",

keywords = "Artificial neural networks, House prices, Multilevel modelling, Predictive accuracy",

author = "Yingyu Feng and Kelvyn Jones",

year = "2015",

month = jul,

day = "8",

doi = "10.1109/ICSDM.2015.7298035",

language = "English",

isbn = "9781479977505",

volume = "1",

pages = "108--114",

booktitle = "2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "Spatial Data Mining and Geographical Knowledge Services (ICSDM), 2015 2nd IEEE International Conference ; Conference date: 08-07-2015 Through 10-07-2015",

}

Feng, Y & Jones, K 2015, Comparing multilevel modelling and artificial neural networks in house price prediction. in 2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015): Proceedings of a meeting held 8-10 July 2015, Fuzhou, China.. vol. 1, 15, Institute of Electrical and Electronics Engineers (IEEE), pp. 108-114, Spatial Data Mining and Geographical Knowledge Services (ICSDM), 2015 2nd IEEE International Conference , Fuzhou, China, 8/07/15. https://doi.org/10.1109/ICSDM.2015.7298035

Comparing multilevel modelling and artificial neural networks in house price prediction. / Feng, Yingyu; Jones, Kelvyn.
2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015): Proceedings of a meeting held 8-10 July 2015, Fuzhou, China.. Vol. 1 Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 108-114 15.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Comparing multilevel modelling and artificial neural networks in house price prediction

AU - Feng, Yingyu

AU - Jones, Kelvyn

PY - 2015/7/8

Y1 - 2015/7/8

N2 - Two advanced modelling approaches, Multi-Level Models and Artificial Neural Networks are employed to model house prices. These approaches and the standard Hedonic Price Model are compared in terms of predictive accuracy, capability to capture location information, and their explanatory power. These models are applied to 2001-2013 house prices in the Greater Bristol area, using secondary data from the Land Registry, the Population Census and Neighbourhood Statistics so that these models could be applied nationally. The results indicate that MLM offers good predictive accuracy with high explanatory power, especially if neighbourhood effects are explored at multiple spatial scales.

AB - Two advanced modelling approaches, Multi-Level Models and Artificial Neural Networks are employed to model house prices. These approaches and the standard Hedonic Price Model are compared in terms of predictive accuracy, capability to capture location information, and their explanatory power. These models are applied to 2001-2013 house prices in the Greater Bristol area, using secondary data from the Land Registry, the Population Census and Neighbourhood Statistics so that these models could be applied nationally. The results indicate that MLM offers good predictive accuracy with high explanatory power, especially if neighbourhood effects are explored at multiple spatial scales.

KW - Artificial neural networks

KW - House prices

KW - Multilevel modelling

KW - Predictive accuracy

U2 - 10.1109/ICSDM.2015.7298035

DO - 10.1109/ICSDM.2015.7298035

M3 - Conference Contribution (Conference Proceeding)

SN - 9781479977505

VL - 1

SP - 108

EP - 114

BT - 2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - Spatial Data Mining and Geographical Knowledge Services (ICSDM), 2015 2nd IEEE International Conference

Y2 - 8 July 2015 through 10 July 2015

ER -

Feng Y, Jones K. Comparing multilevel modelling and artificial neural networks in house price prediction. In 2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM 2015): Proceedings of a meeting held 8-10 July 2015, Fuzhou, China.. Vol. 1. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 108-114. 15 doi: 10.1109/ICSDM.2015.7298035

Comparing multilevel modelling and artificial neural networks in house price prediction

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this