Development of an analytical framework for AEC dispute cost analysis with hybrid feature selection and machine learning
Journal of Asian Architecture and Building Engineering, 2026 (SCI-Expanded, AHCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2026
- Doi Numarası: 10.1080/13467581.2026.2694127
- Dergi Adı: Journal of Asian Architecture and Building Engineering
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Arts and Humanities Citation Index (AHCI), Scopus, Art Source, Compendex, Index Islamicus, Directory of Open Access Journals, Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: Architecture, Engineering and Construction (AEC), construction disputes, dispute cost analysis, hybrid feature selection, machine learning
- Bursa Uludağ Üniversitesi Adresli: Evet
Özet
Disputes are a persistent feature of the Architecture, Engineering, and Construction (AEC) sector, often resulting in cost overruns, schedule delays, and strained contractual relationships. This study develops an analytical framework that systematically quantifies and examines dispute-related costs, while clarifying the key factors underlying their magnitude and variation. In this context, a conceptual framework was established through prior research and semi-structured interviews. Using this framework, data from 181 real dispute cases were collected and analyzed. A hybrid feature-selection method combined mutual information with multiple machine learning (ML) models (e.g. K-Nearest Neighbors, Support Vector Machines, CatBoost, Random Forest, Logistic Regression, and a voting ensemble), and SHapley Additive exPlanations (SHAP) analysis was used to support prediction model interpretation. Overall, the ensemble model outperformed single algorithms. The analysis identified attributes associated with cost outcomes, including the disputant party’s role, payment method, contractor misbidding, number of prior collaborations, compliance with contract terms, adverse weather conditions, expected duration of future collaboration, and extra payment claims. These findings demonstrate the potential of ML to support dispute-cost assessment and decision making. The study contributes a structured approach for evaluating dispute-related costs in the AEC industry and highlights attributes that may help professionals and stakeholders manage disputes more effectively.