# Research on Accurate House Price Analysis by Using GIS Technology and Transport Accessibility: A Case Study of Xi’an, China

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Data Source

#### 2.2. Analysis Framework

#### 2.3. Data Processing

#### 2.3.1. Walking Accessibility

#### 2.3.2. Bus Accessibility

#### 2.3.3. Metro Accessibility

## 3. Experimental Results

#### 3.1. Real Estate Price Estimation for RF

#### 3.2. Real Estate Price Estimation for GBDT

#### 3.3. Real Estate Price Estimation for LGBM

#### 3.4. Real Estate Price Estimation for Stacking

#### 3.5. Model Comparison

## 4. Discussion

## 5. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## Data Availability

## References

- Yiuc, Y.; Wong, S.K. The effects of expected transport improvements on housing prices. Urban Stud.
**2005**, 42, 113–125. [Google Scholar] - Dube, J.; Legros, D.; Theriault, M. A Spatial Difference-in-differences estimator to evaluate the effect of change in public mass transit systems on house prices. Transp. Res. Part B
**2014**, 64, 24–40. [Google Scholar] [CrossRef] - Levkovich, O.; Rouwendal, J.; Van, M.R. The effects of highway development on housing prices. Transportation
**2015**, 43, 379–405. [Google Scholar] - Shyr, O.; Andersson, D.E.; Wang, J.; Huang, T.; Liu, O. Where do home buyers pay most for relative transit accessibility? Hong Kong, Taipei and Kaohsiung Compared. Urban. Stud.
**2013**, 50, 2553–2568. [Google Scholar] [CrossRef] - Mitra, S.K.; Saphores, J.D.M. The value of transportation accessibility in a least developed country city—The case of Rajshahi City, Bangladesh. Transp. Res. Part A Policy Pract.
**2016**, 89, 184–200. [Google Scholar] [CrossRef] - Alonso, W. A reformulation of classical location theory and its relation to rent theory. Pap. Reg. Sci. Assoc.
**1967**, 19, 22–44. [Google Scholar] [CrossRef] - Hansen, W.G. How Accessibility shapes land use. J. Am. Plan. Assoc.
**1959**, 25, 73–76. [Google Scholar] [CrossRef] - Yue, X.; Xu, J.J.; Zhong, Y. Study on the share ratio between a service provider and two carriers. J. China Univ. Posts Telecommun.
**2007**, 14, 120–124. [Google Scholar] [CrossRef] - Shin, K.; Washington, S.; Choi, K. Effects of transportation accessibility on residential property values. Transp. Res. Rec. J. Transp. Res. Board
**2007**, 1994, 66–73. [Google Scholar] [CrossRef] - Zhang, M.; Wang, L. The impacts of mass transit on land development in China: The case of Beijing. Res. Transp. Econ.
**2013**, 40, 124–133. [Google Scholar] [CrossRef] - Salon, D.; (Dora) Wu, J.; Shewmake, S. Impact of bus rapid transit and metro rail on property values in Guangzhou, China. Transp. Res. Rec. J. Transp. Res. Board
**2014**, 2452, 36–45. [Google Scholar] [CrossRef] - Li, S.; Chen, L.; Zhao, P. The impact of metro services on housing prices: A case study from Beijing. Transportation
**2017**, 46, 1291–1317. [Google Scholar] [CrossRef] - Waugh, F.V. Quality Factors influencing vegetable prices J. Farm Econ.
**1928**, 10, 185. [Google Scholar] [CrossRef] - Lancaster, K.J. A new approach to consumer theory. J. Political Econ.
**1966**, 74, 132–157. [Google Scholar] [CrossRef] - Rosen, S. Hedonic Prices and implicit markets: Product differentiation in pure competition. J. Political Econ.
**1974**, 82, 34–55. [Google Scholar] [CrossRef] - Xinru, L.; Chaoqun, M.; Changjun, L. A Research of Benchmark Town Land Price Based on the Hedonic Price Model. Syst. Eng.
**2005**, 23, 115–119. [Google Scholar] - Gao, X.; Asami, Y. Influence of spatial features on land and housing prices. Tsinghua Sci. Technol.
**2005**, 10, 344–353. [Google Scholar] [CrossRef] - Durganjali, P.; Pujitha, M.V. House Resale Price Prediction Using Classification Algorithms. In Proceedings of the 6th IEEE International Conference on Smart Structures and Systems, ICSSS 2019, Chennai, India, 14–15 March 2019; pp. 1–4. [Google Scholar]
- Qian, D.; Nana, S.; Wei, L. Real estate price prediction based on web search data. Stat. Res.
**2014**, 31, 81–88. [Google Scholar] - Bowen, Y.; Buyang, C. Housing price prediction model based on integrated learning. Comput. Knowl. Technol.
**2017**, 13, 191–194. [Google Scholar] - Ke, G.; Meng, Q.; Finley, T.W. LightGBM: A highly efficient gradient boosting decision tree. In Proceedings of the Neural Information Processing Systems Annual Conference, Long Beach, CA, USA, 4–9 December 2017. [Google Scholar]
- Li, C.; Chen, Z.; Liu, J.; Gao, X.; Di, F.; Li, L.; Ji, X. Power Load Forecasting Based on the Combined Model of LSTM and XGBoost. 2019. Available online: https://dl.acm.org/doi/pdf/10.1145/3357777.3357792 (accessed on 1 July 2020).
- Banerjee, D.; Dutta, S. Predicting the housing price direction using machine learning techniques. In Proceedings of the 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, Chennai, India, 21–22 September 2017. [Google Scholar]
- Vineeth, N.; Ayyappa, M.; Bharathi, B. House price prediction using machine learning algorithms. Commun. Comput. Inf. Sci.
**2018**, 423–433. [Google Scholar] - Phan, T.D. Housing price prediction using machine learning algorithms: The case of Melbourne city, Australia. In Proceedings of the International Conference on Machine Learning and Data Engineering, Sydney, Australia, 3–7 December 2018; 2019; pp. 8–13. [Google Scholar]
- Brueckner, J.K. Chapter 20 The structure of urban equilibria: A unified treatment of the muth-mills model. Handb. Reg. Urban Econ.
**1987**, 2, 821–845. [Google Scholar] - Evans, R.D.; Rayburn, W. The Effect of school desegregation decisions on single-family housing prices. J. Real Estate Res.
**1991**, 6, 107–216. [Google Scholar] - Malpezzi, S. Hedonic Pricing Models: A Selective and Applied Review. In Housing Economics and Public Policy; Wiley: Hoboken, NJ, USA, 2002; Volume 10, pp. 67–89. [Google Scholar]
- Diaz, R.B. Impacts of Rail Transit on Property Values; Booz Allen & Hamilton Inc.: McLean, VA, USA, 1999. [Google Scholar]
- Wenjie, W.; Zhilin, L.; Wenzhong, Z. Evaluation of factors influencing residential land price in Beijing based on structural equation model. Acta Geogr. Sin.
**2011**, 065, 676–684. [Google Scholar] - Zhang, W.; Chen, Y. Analysing commerce traffic accessibility based on GIS. In Proceedings of the ITS 14th World Congress on Intelligent Transport Systems, Beijing, China, 9–13 October 2007; pp. 2662–2670. [Google Scholar]
- Wardlaw, A.C. Practical Statistics; John Wiley & Sons Ltd.: West Sussex, UK, 2000. [Google Scholar]

**Figure 1.**Data spatial distribution in Xi’an, China. (

**a**) Urban road network spatial distribution. (

**b**) Housing spatial distribution. (

**c**) Bus spatial distribution. (

**d**) Metro spatial distribution.

**Figure 5.**Pearson correlation coefficient graph of house price and walk accessibility under different radii.

**Figure 8.**Pearson correlation coefficient graph of house price and bus accessibility under different radii.

**Figure 11.**Pearson correlation coefficient graph of house price and metro accessibility under different radii.

K | R² | RMSE |
---|---|---|

1 | 0.883 | 1766.033 |

2 | 0.855 | 1982.18 |

3 | 0.881 | 1811.473 |

4 | 0.898 | 1692.132 |

5 | 0.891 | 1740.391 |

6 | 0.880 | 1836.623 |

7 | 0.892 | 1733.959 |

8 | 0.878 | 1897.477 |

9 | 0.877 | 1833.595 |

10 | 0.887 | 1887.743 |

mean | 0.8852 | 1818.161 |

**Table 2.**Results of the gradient lifting regression tree algorithm (GBDT) with K-fold Cross Validation.

K | R² | RMSE |
---|---|---|

1 | 0.865 | 1895.195 |

2 | 0.833 | 2126.769 |

3 | 0.868 | 1913.237 |

4 | 0.879 | 1850.641 |

5 | 0.864 | 1939.744 |

6 | 0.856 | 2002.727 |

7 | 0.882 | 1804.318 |

8 | 0.858 | 2042.478 |

9 | 0.858 | 1976.505 |

10 | 0.869 | 2028.498 |

mean | 0.8632 | 1958.011 |

K | R² | RMSE |
---|---|---|

1 | 0.859 | 1924.303 |

2 | 0.829 | 2163.15 |

3 | 0.857 | 2051.347 |

4 | 0.845 | 2022.349 |

5 | 0.841 | 1936.352 |

6 | 0.846 | 2060.834 |

7 | 0.867 | 1914.865 |

8 | 0.868 | 2170.805 |

9 | 0.849 | 2024.958 |

10 | 0.842 | 2109.993 |

mean | 0.8503 | 2037.896 |

K | R² | RMSE |
---|---|---|

1 | 0.887 | 1741.581 |

2 | 0.857 | 1974.754 |

3 | 0.884 | 1785.56 |

4 | 0.898 | 1692.202 |

5 | 0.891 | 1736.423 |

6 | 0.883 | 1808.383 |

7 | 0.894 | 1700.266 |

8 | 0.882 | 1866.95 |

9 | 0.879 | 1815.86 |

10 | 0.886 | 1881.999 |

mean | 0.8841 | 1800.398 |

Model | R² | RMSE | Model Scale | Train Time(s) | Run Time(s) |
---|---|---|---|---|---|

RF | 0.891 | 1776.79 | 486 mb | 12.298 s | 0.644 s |

GBDT | 0.863 | 1979.78 | 0.7 mb | 4.705 s | 0.049 s |

LGBM | 0.873 | 1912.71 | 0.8 mb | 0.437 s | 0.043 s |

Stacking | 0.892 | 1761.84 | 488 mb | 93.556 s | 0.755 s |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Xue, C.; Ju, Y.; Li, S.; Zhou, Q.; Liu, Q.
Research on Accurate House Price Analysis by Using GIS Technology and Transport Accessibility: A Case Study of Xi’an, China. *Symmetry* **2020**, *12*, 1329.
https://doi.org/10.3390/sym12081329

**AMA Style**

Xue C, Ju Y, Li S, Zhou Q, Liu Q.
Research on Accurate House Price Analysis by Using GIS Technology and Transport Accessibility: A Case Study of Xi’an, China. *Symmetry*. 2020; 12(8):1329.
https://doi.org/10.3390/sym12081329

**Chicago/Turabian Style**

Xue, Chao, Yongfeng Ju, Shuguang Li, Qilong Zhou, and Qingqing Liu.
2020. "Research on Accurate House Price Analysis by Using GIS Technology and Transport Accessibility: A Case Study of Xi’an, China" *Symmetry* 12, no. 8: 1329.
https://doi.org/10.3390/sym12081329