Comparative analysis of forecasting construction costs via automated machine learning approach and inclusion of economic index
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- KCISCIEScopus
- 저널 순위
- JCR Q3Scopus Q2KCI Q4
- 저널
- KSCE JOURNAL OF CIVIL ENGINEERING30(9) · 2026
- 피인용
- Web of Science 2Scopus 2
- FWCI (Scopus)
- 0
- JCR IF
- JCR 2024 2
- ISSN
- 1226-7988
저자
- 조우원제1저자Pusan Natl Univ, Dept Architectural Engn, Busandaehak Ro 63beon Gil, Busan 46241, South Korea
- Kim, HyunsooDankook Univ, Dept Architectural Engn, 152 Jukjeon Ro, Yongin 16890, Gyeonggi, South Korea
- Park, HyunJungSilla Univ, Dept Architecture, Baekyang Daero 700beon Gil, Busan 46958, South Korea
- Lee, KyeongsukWestern New England Univ, Dept Construct Management, 1215 Wilbraham Rd, Springfield, MA 01119 USA
- 전정호교신저자Pusan Natl Univ, Dept Architectural Engn, Busandaehak Ro 63beon Gil, Busan 46241, South Korea
초록
Construction cost prediction in the early phase of construction projects is crucial for setting the overall budget and facilitating bidding and contracting processes. While research efforts have been made by adopting machine learning (ML) algorithms to develop robust cost prediction models, they often heavily rely on professionals’ domain-specific knowledge and manual work (e.g., hyperparameter optimization). Also, despite the relationship between the economic index and construction costs, it has been minimally integrated into the dataset used to train the algorithms. A promising alternative is to leverage an automated machine learning approach (AutoML) that incorporates a market-sensitive indicator, the Construction Cost Index (CCI). To this end, this paper introduces an AutoML-centered construction cost forecasting approach and demonstrates its effectiveness through internal/external validation, the inclusion of CCI, feature importance analysis, and an investigation of the trade-off between the number of input features and computing efficiency.
키워드
Automated machine learningConstruction costs predictionEconomic indexExternal validationFeature analysis
식별자
- Scopus EID
- 2-s2.0-105041407372
- WoS UID
- 001799979800001



로그인
연구물 목록으로