Using Machine Learning Algorithms to Forecast the Optimal Bidding Rate in Apartment Auctions
2
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
In this paper, we use the machine learning model to make predictions about the winning bid rate of apartments nationwide. The winning bid rate for apartments should consider various variables. There is a possibility that the existing hedonic priming models might predict uncertain results because of methodological constraints. In this paper, we aim to improve the predictions of apartment auction winning rates by utilizing algorithms such as Random Forest, XGBoost, LightGBM, and DNN, which are robust to problems such as nonlinearity and multicollinearity. A total of 111,232 nationwide apartment auction data were learned and tested from January 2010 to June 2020 by using the data provided by the GG auction and macroeconomic variables collected from KOSIS. In addition, a moving window methodology and an extending window methodology are applied considering by the characteristics of the social science data whose probability structure changes over time. Empirical study shows that the Gradient Boosting models outperforms other models in terms of MAPE, RMSE, MedAE, and AbsMean. There is no significant difference between a moving window methodology and an extended window methodology.
Abstract
In this paper, we use the machine learning model to make predictions about the winning bid rate of apartments nationwide. The winning bid rate for apartments should consider various variables. There is a possibility that the existing hedonic priming models might predict uncertain results because of methodological constraints. In this paper, we aim to improve the predictions of apartment auction winning rates by utilizing algorithms such as Random Forest, XGBoost, LightGBM, and DNN, which are robust to problems such as nonlinearity and multicollinearity. A total of 111,232 nationwide apartment auction data were learned and tested from January 2010 to June 2020 by using the data provided by the GG auction and macroeconomic variables collected from KOSIS. In addition, a moving window methodology and an extending window methodology are applied considering by the characteristics of the social science data whose probability structure changes over time. Empirical study shows that the Gradient Boosting models outperforms other models in terms of MAPE, RMSE, MedAE, and AbsMean. There is no significant difference between a moving window methodology and an extended window methodology.
참고문헌 (27)
- Ibbotson RG, "Real estate returns : A comparison with other investments", Real Estate Econ, 12, pp.219~ (1984)
- 김진희, "우리나라 아파트의 특성과 아파트 가격: 분위회귀분석", 산업경제연구, 27(1), pp.173~195 (2014), 한국산업경제학회
- Kim HH, "Determinants of house prices in Seoul auc-tion market", Pac Rim Prop Res J, 21, pp.91~113 (2015)
- Sirignano J, "Deep learning for mort-gage risk", arXiv preprint arXiv:1607.02470, ~ (2016)
- Feng G, "Deep learning for predicting asset returns", arXiv preprint arXiv:1804.09314, ~ (2018)
- 이동원, "KOSPI200 Prediction through Low-Pass Filtered Long Short-Term Memory Algorithm", Quantitative Bio-Science, 39(1), pp.25~31 (2020), 자연과학연구소[DOI]
- 양준혁, "Forecasting the KOSPI 200 Stock Index Based on LSTM Autoencoder", Quantitative Bio-Science, 39(2), pp.101~109 (2020), 자연과학연구소[DOI]
- 이상규, "KOSPI200 Index Prediction Using Sequence-to-Sequence based on Denoising Filter and Attention Mechanism", Quantitative Bio-Science, 39(2), pp.127~135 (2020), 자연과학연구소[DOI]
- Machine learning at central banks, "Chakraborty C", Bank of England, 674~ (2017)
- De Prado ML, "Advances in financial machine learning" (2018), John Wiley & Sons
- Breiman L, "Random forests", Mach Learn, 45, pp.5~32 (2001)
- Learning internal repre-sentations by error propagation, "Rumelhart DE", Institute for Cognitive Science, ~, pp.ICS Report 8506 (1985)
- Rosen S, "Hedonic prices and implicit markets : Product differen-tiation in pure competition", J Polit Econ, 82, pp.34~55 (1974)
- Cropper ML, "On the choice of func-tional form for hedonic price functions", Rev Econ Stat, 70, pp.668~675 (1988)
- Owusu-Ansah A, "A review of hedonic pricing models in housing research", J Int Real Estate Constr Stud, 1, pp.19~ (2011)
- Breiman L, "Bagging predictors", Mach Learn, 24, pp.123~140 (1996)
- Schapire RE, "The strength of weak learnability", Mach Learn, 5, pp.197~227 (1990)
- Chen T, "Xgboost: A scalable tree boosting system", SIG KDD Int’l Conf on Knowledge Discovery and Data Mining, 22, pp.785~794 (2016)
- Ke G, "Light-gbm : A highly efficient gradient boosting decision tree", Adv Neur In, 30, pp.3146~3154 (2017)
- Bergstra J, "Random search for hyper-parameter opti-mization", J Mach Learn Res, 13, pp.281~305 (2012)
- López de Prado M, "The future of empirical finance", J Portfolio Management, 41, pp.140~144 (2015)
- Park JH, "A Study on the effect of winning bids on court share auction -focused on residential properties in Seoul", 석사, pp.2017
- 노한장, "부동산 경매에 있어서 최저매각가격의 기준점 효과 분석", 부동산학연구, 17(4), pp.109~131 (2011), 한국부동산분석학회
- 문희명, "서울시 아파트의 경매 낙찰결정특성", 주거환경, 10(1), pp.73~90 (2012), 한국주거환경학회
- 이홍대, "충남지역 아파트 경매시장의 낙찰 결정요인", 주거환경, 14(1), pp.59~68 (2016), 한국주거환경학회
- Park SC, "Study on the effect of RP Interest rate on a real estate price", J Bus Educ, 4, pp.157~174 (2009)
- Mayer M, "Estimation, updating methods for hedonic valuation", J Eur Real Estate Res, 12, pp.134~150 (2019)