Journal of the Korea Institute of Building Construction (한국건축시공학회지)

The Korean Institute of Building Construction (한국건축시공학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of the Construction Cost Prediction Performance according to Feature Scaling and Log Conversion of Target Variable

피처 스케일링과 타겟변수 로그변환에 따른 건축 공사비 예측 성능 분석

  • Kang, Yoon-Ho (Graduate School, GyeongSang National University) ;
  • Yun, Seok-Heon (Department of Architectural Engineering, GyeongSang National University)
  • Received : 2022.05.18
  • Accepted : 2022.06.10
  • Published : 2022.06.20
Download PDF
⟨ Previous Next ⟩

Abstract

With the development of various technologies in the area of artificial intelligence, a number of studies to application of artificial intelligence technology in the construction field are underway. Diverse technologies have been applied to the task of predicting construction costs, and construction cost prediction technologies applying artificial intelligence technologies have recently been developed. However, it is difficult to secure the vast amount of construction cost data required for machine learning, which has not yet been practically used. In this study, to predict the construction cost, the latest artificial neural network(ANN) method is used to propose a method to improve the construction cost prediction performance. In particular, to improve predictive performance, a log conversion method of target variables and a feature scaling method to eliminate the difference in the relative influence of each column data are applied, and their performance in predicting construction cost is compared and analyzed.

건설 분야에서 머신러닝(Machine learning)에 필요한 방대한 공사비 자료를 확보하는 데 어려움이 있어, 아직은 실용적으로 활용되지는 못하고 있다. 본 연구에서는 이러한 공사비 예측을 위하여 최신의 인공신경망(ANN) 방법을 사용하여, 공사비 예측성능을 향상 시키기 위한 방법을 제시하고자 한다. 특히 타겟변수를 로그 변환하는 방식, 피처스케일링 방식을 적용하고자 하였으며, 이들의 공사비 예측성능을 비교 분석하고자 한다. 이는 향후 다양한 조건을 갖는 공사비 예측과 적정 공사비 검증에 도움을 줄 수 있을 것으로 예측된다.

Keywords

Acknowledgement

This research was supported by the National Research Foundation of Korea(NRF) funded by the Ministry of Education(NRF-2019R1A2C1005833).

References

  1. Seo YG. A model study for predicting construction costs in the planning and design stages through performance construction cost analysis [master's thesis]. [Seoul (Korea)]: Korea University. 2009. 62 p.
  2. Jung SH, Kwon OB, Son JH. A study on the analysis and estimation of the construction cost by using deep learning in the SMART educational facilities -Focused on planning anf design stage-. Journal of Korean Institute of Educational Facilities. 2018 Nov;25(6):35-44. https://doi.org/10.7859/kief.2018.25.6.035
  3. Oh JH, Kim JS. Prediction of housing price using machine learning:Focusing on MARS. Korean Association for Housing Policy Studies Symposium; 2017 Nov; Seoul, Korea. Seoul (Korea): Korean Association for Housing Policy Studies; 2017. p. 153-71.
  4. Hyun CT, Hong TH, Son MJ, Kim YS, Jang DW. Development of the construction cost prediction model based on case-based reasoning in the planning phase of mega-project. Journal of the Architectural Institute of Korea Structure & Construction. 2009 May;25(9):181-90.
  5. Tayefeh Hashemi S, Ebadati OM, Kaur H. Cost estimation and prediction in construction projects: a systematic review on machine learning techniques. SN Applied Sciences. 2020 Sep;2:1703. https://doi.org/10.1007/s42452-020-03497-1
  6. Pham TQD, Quang NH, Vo ND, Bui VS, Tran VX. Fast and Accurate Estimation of Building Cost Using Machine Learning. Research in Intelligent and Computing in Engineering. 2021 Jan;1254:515-25. https://doi.org/10.1007/978-981-15-7527-3_49
  7. Zhirui Z. Analysis and prediction of housing prices in shenyang city based on elman neural network. Scholars Journal of Engineering and Technology. 2021 Nov;9(10):159-63. https://doi.org/10.36347/sjet.2021.v09i10.001