DOI QR코드

DOI QR Code

데이터 마이닝을 이용한 아파트 초기계약 예측모형 개발: 위례 신도시 미분양 아파트 단지를 사례로

Development of Forecasting Model for the Initial Sale of Apartment Using Data Mining: The Case of Unsold Apartment Complex in Wirye New Town

  • 투고 : 2018.10.23
  • 심사 : 2018.12.20
  • 발행 : 2018.12.28

초록

이 연구에서는 미분양 아파트 단지의 세대별 계약 자료에 데이터 마이닝 기법인 의사결정나무, 신경망, 로지스틱 모형을 적용하여 세대별 초기계약을 예측하는 모형을 개발한다. 모형 개발에는 위례신도시 미분양 아파트 단지의 계약 자료가 이용되며, 이 자료는 훈련용 자료와 검정용 자료로 분할되어 분석에 투입된다. 훈련용 자료에서는 신경망, 의사결정나무, 로지스틱 모형 순으로 예측력이 뛰어났지만 검정용 자료에서는 로지스틱 모형이 가장 우수하게 나타났다. 이 같은 결과는 신경망이 훈련용 자료에 최적화된 모형으로 구축되면서 검정용 자료에 대한 적응성이 떨어져 나타난 결과로 판단된다. 의사결정나무와 로지스틱 모형을 병행 적용한 결과, 층수, 향, 세대 위치, 전기 및 발전기실의 소음, 청약자 거주지, 청약 종류가 초기계약에 영향을 주는 것으로 나타났다. 이는 두 가지 모형을 같이 사용하는 것이 초기계약 결정요인 발굴에 더 효과적이라는 것을 의미한다. 이 연구는 데이터 마이닝의 적용 범위를 주택 분양 예측까지 확장함으로써 융복합 분야 발전에 기여하고 있다.

This paper aims at applying the data mining such as decision tree, neural network, and logistic regression to an unsold apartment complex in Wirye new town and developing the model forecasting the result of initial sale contract by house unit. Raw data are divided into training data and test data. The order of predictability in training data is neural network, decision tree, and logistic regression. On the contrary, the results of test data show that logistic regression is the best model. This means that logistic regression has more data adaptability than neural network which is developed as the model optimized for training data. Determinants of initial sale are the location of floor, direction, the location of unit, the proximity of electricity and generator room, subscriber's residential region and the type of subscription. This suggests that using two models together is more effective in exploring determinants of initial sales. This paper contributes to the development of convergence field by expanding the scope of data mining.

키워드

DJTJBT_2018_v16n12_217_f0001.png 이미지

Fig. 1. SAS E-Miner flow chart

DJTJBT_2018_v16n12_217_f0002.png 이미지

Fig. 2. Results of decision tree analysis

DJTJBT_2018_v16n12_217_f0003.png 이미지

Fig. 3. Structure of multi-layered neural network

Table 1. Composition of subscription

DJTJBT_2018_v16n12_217_t0001.png 이미지

Table 2. Contract rate of initial sale

DJTJBT_2018_v16n12_217_t0002.png 이미지

Table 3. Variables for data mining

DJTJBT_2018_v16n12_217_t0003.png 이미지

Table 4. Statistics of decision tree analysis

DJTJBT_2018_v16n12_217_t0004.png 이미지

Table 5. Classification rate of decision tree analysis

DJTJBT_2018_v16n12_217_t0005.png 이미지

Table 6. RMSE by the number of hidden nodes

DJTJBT_2018_v16n12_217_t0006.png 이미지

Table 7. Statistics of neural network analysis

DJTJBT_2018_v16n12_217_t0007.png 이미지

Table 8. Classification rate of Neural network analysis

DJTJBT_2018_v16n12_217_t0008.png 이미지

Table 11. Results of logistic regression analysis

DJTJBT_2018_v16n12_217_t0009.png 이미지

Table 9. Statistics of logistic regression analysis

DJTJBT_2018_v16n12_217_t0010.png 이미지

Table 10. Classification rate of logistic regression

DJTJBT_2018_v16n12_217_t0011.png 이미지

Table 12. Comparison of final models

DJTJBT_2018_v16n12_217_t0012.png 이미지

Table 13. Comparison of determinants by model

DJTJBT_2018_v16n12_217_t0013.png 이미지

참고문헌

  1. M. S. Baik & J. C. Shin. (2011). A Study on the Determinants of Initial Sales Rate for New Apartment Housing. Journal of the Korean Urban Management Association, 24(1), 213-237.
  2. M. S. Baik & J. C. Shin. (2011). A Study on the Condominium Sales Marketing Activities and Initial Sales Rate. Journal of the Korea Real Estate Analysts Association, 17(3), 25-43.
  3. H. S. Kwon & D. W. Bang. (2015). A Study on the Cause of Difference between New Apartment Subscription Rate and Initial Pre-sale Contract Rate. Housing Studies Review, 23(3), 111-143.
  4. G. S. Linoff & M. J. Berry. (2018). Data Mining Techniques: For Marketing, Sales, and Customer Relation management. Seoul : Hankyngsa.
  5. M. H. Huh & Y. G. Lee. (2008). Data Mining Modeling and Cases. Seoul : Hannarae Publishing Co.
  6. Y. H. Kim & S. S. Ahn. (2006). A Study on the Characteristics of Fast-food Restaurant's Customers. Tourism & Leisure Research, 18(2), 191-209.
  7. W. J. Kim, Y. S. Choi & D. H. Yoo. (2018). Development of Win-Loss Prediction Models and Strategies for Improving Winning Rate of the Korean Professional Baseball Teams Using Data Mining Techniques. Korea Journal of Sport Management, 23(3), 88-104. https://doi.org/10.31308/KSSM.23.3.6
  8. J. Y. Oh & S. H. Choi. (2018). An Analysis of the Characteristics of Companies introducing Smart Factory System Using Data Mining Technique. Journal of the Korea Convergence Society, 9(5), 179-189. https://doi.org/10.15207/JKCS.2018.9.5.179
  9. H. J. Chun. (2015). A Study on Korean Household Income Using Data Mining. Journal of the Korea Planning Association, 50(2), 227-241.
  10. K. M. Kim & C. K. Kim. (2017). Forecasting of Investment Characteristics of Global REITs Using Data Mining. Korea Real Estate Review, 68, 44-56
  11. J. Y. Lee, M. H. Choi & S. Y. Lee. (2007). A Study on the Forecasting Model of Apartment Price Based on Data Mining. Journal of the Korea Planning Association, 42(4), 135-148.
  12. H. J. Chun. (2017). A Study on the Determinants of Housing Price Using Data Mining, Residential Environment: Journal of The Residential Environment Institute of Korea, 15(3), 35-46.
  13. B. C. Kim, Y. Kim, M. Kim & J. S. Lee. (2018). Using Data Mining Techniques to Model Housing Rental Price near Universities in Seoul. Journal of the Korean Institute of Industrial Engineers, 44(4), 259-271. https://doi.org/10.7232/JKIIE.2018.44.4.259
  14. A. R. Hong, J. P. Ko & S. J. Yoo. (2010). A Study on the Forecasting Model of the Investment Characteristics of Seoul Office Buildings based on Data Mining. Seoul Studies, 11(2), 51-68.
  15. K. S. Mun, J. G. Choi & H. S. Lee. (2015). An Analysis for Price Determinants of Small and Medium-Sized Office Buildings Using Data Mining Method in Gangnam-Gu. International Journal of Contents, 15(7), 414-427.
  16. P. W. Huh, S. Y. Kim, Y. S. Hong & G. E. Shim. (2014). A Study on the Determinants of Office Building Property Management Method in Seoul. Seoul Studies, 15(3), 41-57.
  17. H. S. Lee. (2004). A Study on Preference Characteristics for Each Condominium in a Same Site on Initial and Re-sales Markets Using Survival Analysis. Journal of the Korea Planning Association, 39(3), 81-93.
  18. T. Y. Kim & C. M. Lee. (2005, November). Comparative Study on Renter's Choice with Data Mining Techniques. 2005 Spring Congress of Korea Planning Association.
  19. H. Byeon. (2017). Exploring Influence Factors for Peer Attachment in Korean Youth Based on Multi-Layer Perceptron Artificial Neural Networks. Journal of the Korea Convergence Society, 8(10), 209-214. https://doi.org/10.15207/JKCS.2017.8.10.209
  20. T. S. Ki & S. H. Lee. (2017). A Prediction Scheme for Power Apparatus using Artificial Neural Networks. Journal of Convergence for Information Technology, 7(6), 201-207. https://doi.org/10.22156/CS4SMB.2017.7.6.201
  21. H. Yoon. (2018). Classificatin of Normal and Abnormal Heart Sounds Using Neural Network. Journal of Convergence for Information Technology, 8(5), 131-135. https://doi.org/10.22156/CS4SMB.2018.8.5.131
  22. S. Y. Lee. (2003). A Study on Data Application Using Data Mining. Master dissertation. Yonsei University, Seoul.
  23. B. S. Kim, W. S. Bae, K. H. Seok, D. H. Cho. & K. L. Choi. (2018). SAS EM 14.1. Seoul : Kyowoo.
  24. J. H. Kim. (2008). The Effect of the Landscape Visibility of a Golf Course on Apartment Price: A Case Study of the Residential Area around Hansung C.C. in Yong-in City. Journal of The Korean Regional Development Association, 20(4), 69-88.
  25. H. G. Sung & J. Y. Kim. (2011). The Impacts of Time-Varying Accessibility of Facilities on Housing Price Change by the Modified Repeat Sales Model - The Case of Subway Line 9 in Seoul. Journal of the Korean Society of Civil Engineers, D31(3D), 477-487.
  26. M. K. Oh & J. H. Cho. (2018). Newly Improved Incineration Plant's Impacts on Nearby Apartment Sale Prices with Interrupted Time Series Analysis, Journal of Korea Planning Association, 53(3), 145-159. https://doi.org/10.17208/jkpa.2018.06.53.3.145