Advertisement

KSCE Journal of Civil Engineering

, Volume 23, Issue 12, pp 4984–4991 | Cite as

Short-term Forecast Model of Apartment Jeonse Prices using Search Frequencies of News Article Keywords

  • Hojun Kang
  • Kanghyeok Lee
  • Do Hyoung ShinEmail author
Construction Management
  • 17 Downloads

Abstract

Housing prices, including Jeonse prices, are impacted by human psychological attitudes. News articles are one of the factors that influence such human psychological attitudes. Previous studies have confirmed the potential for utilization of news articles in the analysis of the real estate market. However, no actual studies on real estate price forecasting through news articles have yet been carried out. Accordingly, the present study proposes a short-term forecast model of apartment Jeonse prices through big data analysis of news articles. The forecast model was a regression model using Jeonse prices for apartments in the Pangyo area as the dependent variable and the Internet search frequency of news article keywords as the independent variable. The news article-based forecast model was created from the independent variable made as a combination of 4 keywords with a time shift of 10 months. Comparison with time-series models frequently used for real estate price forecasting showed that the model was superior in terms of forecast accuracy and forecast lead time. It is expected that use of the news article-based forecast model according to the present study will allow for the establishment of more effective Jeonse price-related policies.

Keywords

big data news articles forecasting model lease price apartment 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgements

This work was supported by an Inha University Research Grant.

References

  1. Asuero, A. G., Sayago, A., and Gonzalez, A. G. (2006). “The correlation coefficient: An overview.” Critical Reviews in Analytical Chemistry, Vol. 36, No. 1, pp. 41–59, DOI:  https://doi.org/10.1080/10408340500526766.CrossRefGoogle Scholar
  2. Bang, S. (2010). Three essays relevant to housing price index: SPAR index, index smoothing, relationship between housing price and transaction volume, PhD Dissertation, Hansung University, Seoul, Korea.Google Scholar
  3. Cauley, S. D., and Pavlov, A. D. (2002). “Rational delays: The case of real estate.” The Journal of Real Estate Finance and Economics, Vol. 24, No. 1, pp. 143–165, DOI:  https://doi.org/10.1023/A:1013990523388.CrossRefGoogle Scholar
  4. Choi, H. and Varian, H. (2012). “Predicting the present with Google trends.” Economic Record, Vol. 88, No. s1, pp. 2–9, DOI:  https://doi.org/10.1111/j.1475-4932.2012.00809.x.CrossRefGoogle Scholar
  5. Engelhardt, G. V. (2003). “Nominal loss aversion, housing equity constraints, and household mobility: Evidence from the United States.” Journal of Urban Economics, Vol. 53, No. 1, pp. 171–195, DOI:  https://doi.org/10.1016/S0094-1190(02)00511-9.CrossRefGoogle Scholar
  6. Gayer, T. and Viscusi, W. K. (2002). “Housing price responses to newspaper publicity of hazardous waste sites.” Resource and Energy Economics, Vol. 24, No. 1, pp. 33–51, DOI:  https://doi.org/10.1016/S0928-7655(01)00047-1.CrossRefGoogle Scholar
  7. Genesove, D. and Mayer, C. (2001). “Loss aversion and seller behavior: Evidence from the housing market.” Quaterly Journal of Economics, Vol. 116, No. 8143, pp. 1233–1260, DOI:  https://doi.org/10.1162/003355301753265561.CrossRefGoogle Scholar
  8. Ginsberg, J., Mohebbi, M. H., Patel, R. S., Brammer, L., Smolinski, M. S., and Brilliant, L. (2009). “Detecting influenza epidemics using search engine query data.” Nature, Vol. 457, pp. 1012–1014, DOI:  https://doi.org/10.1038/nature07634.CrossRefGoogle Scholar
  9. Hur, Y., Jang, K., Kim, S., and Kim, H. (2008). “The granger casuality analysis between prices and trading volume in the housing market.” Housing Studies Review, Vol. 16, No. 4, pp. 49–70 (in Korean).Google Scholar
  10. Internet Trend (2016). “Weblog analysis report: Internet trend/search engine.” Internet Trend, http://trend.logger.co.kr/trendForward.tsp, [Accessed on October 3, 2016].
  11. Jin, C. and Gallimore, P. (2012). “Newspaper content and home prices: Perception, reasoning and affect.” Journal of the Korea Real Estate Analysis Association, Vol. 18, No. 2, pp. 125–142 (in Korean).Google Scholar
  12. KAB (2016). “Statistics for land sales.” Korea Appraisal Board, http://www.r-one.co.kr/rone/resis/statistics/statisticsViewer.do, [Accessed on October 3, 2016].
  13. Kim, J. (2006). “Influence of newspaper articles on real estate market.” Housing Studies Review, Vol. 14, No. 2, pp. 39–63 (in Korean).Google Scholar
  14. Kim, S. and Shin, D. (2016). “Forecasting short-term air passenger demand using big data from search engine queries.” Automation in Construction, Vol. 70, pp. 98–108, DOI:  https://doi.org/10.1016/j.autcon.2016.06.009.CrossRefGoogle Scholar
  15. Kim, D. and Yu, J. (2016). “How does news article affect on the apartment sale and chonsei price regime duration.” Seoul Studies, Vol. 17, No. 2, pp. 29–46 (in Korean).Google Scholar
  16. KOSIS (2015). “Housing type by administrative area.” Korean Statistical Information Service, http://kosis.kr/statHtml/statHtml.do?orgId=116&tblId=DT_MLTM_5402&conn_path=I3, [Accessed on October 18, 2016].
  17. Kwon, J., Kim, Y., Kim, K., and Lee, H. (2005). A study on forecasting model of Korea housing, Research Report 2005–4, Korea Housing Institute, Seoul, Korea (in Korean).Google Scholar
  18. Lim, J. (2011). “Do housing trading volume explain housing prices or the converse?.” The Korea Spatial Planning Review, Vol. 69, pp. 3–18, DOI:  https://doi.org/10.15793/kspr.2011.69..001.CrossRefGoogle Scholar
  19. Lim, S. (2016). “Comparison of the forecasting models with real estate price index.” Journal of the Korean Data and Information Science Society, Vol. 27, No. 6, pp. 1573–1583, DOI:  https://doi.org/10.7465/jkdi.2016.27.6.1573.CrossRefGoogle Scholar
  20. McLaren, N. and Shanbhogue, R. (2011). “Using internet search data as economic indicators.” Bank of England Quarterly Bulletin, Vol. 51, No. 2, pp. 134–140, DOI:  https://doi.org/10.2139/ssrn.1865276.Google Scholar
  21. MOLIT (2014). Korea housing survey: Statistics report, Ministry of Land, Infrastructure and Transport, Sejong, Korea.Google Scholar
  22. MOLIT (2016). “Housing price inquiry system.” Ministry of Land, Infrastructure and Transport, http://rt.molit.go.kr/, [Accessed on October 18, 2016].
  23. Naver (2016a). “Naver data lab.” Naver, https://datalab.naver.com/keyword/trendSearch.naver [Accessed on October 3, 2016].
  24. Naver (2016b). “Naver search advertisement.” Naver, https://searchad.naver.com, [Accessed on October 3, 2016].
  25. Preis, T., Moat, H. S., and Stanley, H. E. (2013). “Quantifying trading behavior in financial markets using Google trends.” Scientific Reports, Vol. 3, 1684, pp. 1–6, DOI:  https://doi.org/10.1038/srep01684.Google Scholar
  26. Son, J., Kim, K., and Kim, Y. (2002). “A study on the forecasting model of real estate market: The case of Korea.” Housing Studies Review, Vol. 11, No. 1, pp. 49–74 (in Korean).MathSciNetGoogle Scholar
  27. Song, H. (2002). “A study on real estate price forecasting by time series model.” MSc Thesis, Konkuk University, Seoul, Korea.Google Scholar
  28. Woo, Y. and Lee, E. (2011). “An analysis on the relationship between media coverage and time-series housing prices.” Housing Studies Review, Vol. 19, No. 4, pp. 111–134 (in Korean).Google Scholar

Copyright information

© Korean Society of Civil Engineers 2019

Authors and Affiliations

  1. 1.Dept. of Civil EngineeringInha UniversityIncheonKorea

Personalised recommendations