Classification of construction clients payment histories based on contractor analysis using regression tree and clustering algorithm

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: Classification of construction clients payment histories based on contractor analysis using regression tree and clustering algorithm

ارائه دهنده: Provider: Nima Hojat

اساتید راهنما: Supervisors: S Mahdi Hosseinian

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: Javad Taherinejad and Mohsen Babaei

زمان و تاریخ ارائه: Time and date of presentation: 2024

مکان ارائه: Place of presentation: Faculty of Engineering

چکیده: Abstract: The complexities of project owners' payment behavior in construction have often been overlooked, hindering a comprehensive understanding of payment processes. This paper introduces an innovative framework that evaluates such behavior by employing both supervised and unsupervised algorithms, including regression trees and k-means clustering. Through this framework, project owners are categorized into nine distinct groups, each characterized by unique payment behavior attributes. The dataset focuses on diverse payment methods used by owners within eight weeks post-claim submission, encompassing various scenarios linked to payment profiles. The proposed models were evaluated on a sample of 32 Iranian construction projects. Most owners who completed payments experienced a one-week delay, with a payment period averaging three weeks, and made payments ranging from 60% to 80% within a single payment period, establishing them as the most favorable owners compared to other groups. Conversely, owners with incomplete payments typically encountered delays of less than one week, had a payment period averaging 2 weeks, made payments of 30% to 60% within one payment period, and reached a maximum total project payment of 70% within eight weeks after submitting the claim. The decision tree achieved an 88% accuracy rate in predicting owner payment behavior, while the K-means model successfully predicted all owners’ payment behavior. This study offers valuable insights for contractors, aiding in predicting owner payment behavior to support risk-informed decision-making during tendering and improving cash flow forecasting. It also provides project owners with opportunities to optimize operational strategies and payment procedures by benchmarking against industry peers

فایل: ّFile: Download فایل