Forecasting contractor's deviation from the client objectives in prequalification model using support vector regression

Attar, Amirhossein Movahedian; Khanzadi, Mostafa; Dabirian, Shahin; Kalhor, Elmira

doi:10.1016/j.ijproman.2012.11.002

Cited by 20 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [ 41 ] used drones to capture aerial images of a small tank farm in Termini Imerese, Italy, to create a risk register. Cheng and Roy [ 25 ] and [ 54 ] used simulated or linguistic data to create artificial intelligence models that are characterized in the model as digital assets.…”

Section: Discussionmentioning

confidence: 99%

Digital Assets for Project-Based Studies and Project Management

Miller¹

2021

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

This research provides a literature survey of digital assets available through a project; specifically, it identifies sources of data that can be used for practicing data-driven, context-specific project management, or for project-based academic research. Projects are key vehicles for economic and social action, and they are also a primary source of innovation, research, and organizational change. The project boundaries of time, tasks, and people define a rich environment for collecting behavioral and attitudinal data for learning opportunities and academic research. Based on a systematic literature review of the top four project management journals, this research identifies four categories of data sources – communications, reports/records, model representations, and computer systems – and 52 digital assets. The list of digital assets can be inputs for the creation of project artifacts as well as sources for monitoring and controlling project activities and for sense-making in retrospectives or lessons learned. In an illustrative case, this research uses three of the digital assets, social network analysis, and topic modeling to analyze the verbal and written communications between project participants. The classification model and categorization are useful for decision support and artificial intelligence systems model development that requires real-world data.

show abstract

Section: Discussionmentioning

confidence: 99%

Digital Assets for Project-Based Studies and Project Management

Miller¹

2021

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

show abstract

“…SVM are developed mainly by Vapnik (2000) based on structural risk minimization, and have been shown to ensure good generalization (Movahedian Attar et al , 2013), An et al (2007b) apply SVM to classify the accuracy of cost estimations for 62 Korean building projects and for regression purposes; and Movahedian Attar et al (2013) use support vector regression (SVR) to forecast how far contractors deviate from client expectations during contractor prequalification, and find that SVR performs better than ANN. Son et al (2012) use principal component analysis (PCA)–SVR, a SVM approach aided by PCA to reduce dimensions, to predict the construction costs of 84 building projects.…”

Section: Literature Reviewmentioning

confidence: 99%

Hybrid approach to reducing estimating overfitting and collinearity

Xiong

Newton

et al. 2019

ECAM

View full text Add to dashboard Cite

PurposeThe purpose of this paper is to present an approach to address the overfitting and collinearity problems that frequently occur in predictive cost estimating models for construction practice. A case study, modeling the cost of preliminaries is proposed to test the robustness of this approach.Design/methodology/approachA hybrid approach is developed based on the Akaike information criterion (AIC) and principal component regression (PCR). Cost information for a sample of 204 UK school building projects is collected involving elemental items, contingencies (risk) and the contractors’ preliminaries. An application to estimate the cost of preliminaries for construction projects demonstrates the method and tests its effectiveness in comparison with such competing models as: alternative regression models, three artificial neural network data mining techniques, case-based reasoning and support vector machines.FindingsThe experimental results show that the AIC–PCR approach provides a good predictive accuracy compared with the alternatives used, and is a promising alternative to avoid overfitting and collinearity.Originality/valueThis is the first time an approach integrating the AIC and PCR has been developed to offer an improvement on existing methods for estimating construction project Preliminaries. The hybrid approach not only reduces the risk of overfitting and collinearity, but also results in better predictability compared with the commonly used stepwise regression.

show abstract

“…Several researchers (Niento-Morote & Ruz-Vila, 2012; Assaf et al, 2017;Polat, 2016;Hasnain, Thaheem, & Ullah, 2018;Attar, Khanzadi, Dabirian, & Kalhor, 2013) determined contractor selection sub-criteria, which has grouped into principal criteria.…”

Section: Criteria Discussedmentioning

confidence: 99%

Criteria Evaluation for Contractor Selection in Cultural Heritage Projects Using Multiple Criteria Approach

Morkūnaitė

Podvezko

2019

17th International Colloquium „Sustainable Decisions in Built Environment

View full text Add to dashboard Cite

The low bid is the most common applicable method in the contractor selection process, considering by only one dominant criterion. However, the lowest price criterion not allows selecting qualified, responsible, sophisticated, and knowledgeable contractor for cultural heritage projects. Moreover, the improper contractor selection may induce claims, litigation, and poor quality work, increased costs for project performance or management. Selection of appropriate contractor is very important for the success and excellent accomplishment of cultural heritage projects. This study presents criteria evaluation for contractor selection in cultural heritage projects. This paper provides reviews of contractor selection and proposed criteria evaluation, and determines the criteria of culture heritage contractor selection. This study applies the multiple criteria approach: AHP, PROMETHEE and EDAS approaches.

show abstract

Forecasting contractor's deviation from the client objectives in prequalification model using support vector regression

Cited by 20 publications

References 25 publications

Digital Assets for Project-Based Studies and Project Management

Digital Assets for Project-Based Studies and Project Management

Hybrid approach to reducing estimating overfitting and collinearity

Criteria Evaluation for Contractor Selection in Cultural Heritage Projects Using Multiple Criteria Approach

Contact Info

Product

Resources

About