Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 84
PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON ENGINEERING COMPUTATIONAL TECHNOLOGY
Edited by: B.H.V. Topping, G. Montero and R. Montenegro
Paper 130

A Case-Based Reasoning Prototype for Construction Subcontractor Registration

S.T. Ng1 and C.D.T. Luu2

1Department of Civil Engineering, The University of Hong Kong, HKSAR
2QUASAR Constructions Pty Ltd, Australia

Full Bibliographic Reference for this paper
S.T. Ng, C.D.T. Luu, "A Case-Based Reasoning Prototype for Construction Subcontractor Registration", in B.H.V. Topping, G. Montero, R. Montenegro, (Editors), "Proceedings of the Fifth International Conference on Engineering Computational Technology", Civil-Comp Press, Stirlingshire, UK, Paper 130, 2006. doi:10.4203/ccp.84.130
Keywords: construction subcontractor, case-based reasoning, subcontractor registration.

Summary
It is widely recognised that the broker-type subcontracting system creates non value-adding layers in the project delivery team. Several industry reports for example reference [1] point to the establishment and maintenance of a construction subcontractor registration system. Having a more informed framework for tracking subcontractor capabilities and performance is no doubt significant to the industry [2], as it could help eliminate the inherently unsuitable subcontractors from participating in the construction process and hence cut down on the amount of repeated or abortive work.

However, as there are different categories of specialised trades, one could expect that the nature of work could vary significantly between the labour intensive and plant intensive subcontractors. As a result, engineering judgement of decision-makers is called upon when evaluating the candidates. Case-based reasoning (CBR) being a decision approach built upon the notion of reusing experiential knowledge may provide a rational yet flexible means for establishing the decision criteria for evaluating subcontractors of different kinds [3].

With this in mind, a mechanism for scrutinising the information collected from the subcontractors based on the CBR approach is devised. The proposed case-based subcontractor registration system consists of four essential components namely the input, criteria formulation, subcontractor evaluation and output modules.

The input module allows users to enter relevant information regarding the current project. To initiate the process, users are prompted to enter certain general information such as the category and scale of the subcontracting work applying in the case of an application for inclusion in the approved list. Otherwise, the system will prompt the user to key in the project characteristics and objectives if the evaluation is for the compilation of a subcontractor list for a specific project.

The purpose of the criteria formulation module is to draw up a list of subcontractor assessment criteria and recommended weighting to reflect the distinct characteristics of a particular category and size of subcontractors and works. Through this module, criteria and weightings adopted in similar past projects are retrieved from the case-base. After suitable modification to suit the current situation, the list of evaluation criteria and weightings compiled will form the basis for the rest of the evaluation.

Companies seeking registration or those that wish to be considered for renewal and, or upgrading their registration status will be prompted to submit relevant data. Then, the subcontractor evaluation module would evaluate the organisational and performance data, e.g. the financial, technical and managerial abilities of the applicant by comparing those with a comparable subcontractor within the same category and price range. The performance of the most similar subcontractors will be the basis for decision-makers to determine whether greater caution should be taken with respect to the applicant.

The output module reports the recommendations to the user for decision support. As mentioned earlier, the criteria formulation module will generate a list of evaluation criteria and the recommended weightings for the new project. This is reported through the output module for the user's consideration. The decisions of the subcontractor evaluation process are whether the subcontractor shall be registered on the list of the applied category without condition or for a probationary period. The results also include the maximum capacity of work a subcontractor can handle.

Based upon the above mechanism, the information requirements for the development of the case-based reasoning model including the case input, case matching and retrieval, as well as case output and outcome are identified. With this structure, historic information regarding the registration decisions as well as the registered subcontractors can be represented in cases in a structured manner.

A preliminary rapid prototype is developed using ART*Enterprise to demonstrate the concept and illustrate the functions of the case-based subcontractor registration system. It is clear that the CBR approach can be applied to subcontractor registration. The next stage of this study is to continue to develop the case-based subcontractor registration model and collect more cases for testing.

References
1
Tang, H. "Construct for Excellence", report of the construction industry review committee, The Printing Department, HKSAR, 2001.
2
Tserng, H.P. and Lin, P.H. "An accelerated subcontracting and procuring model for construction projects", Automation in construction, 11, 105-125, 2002. doi:10.1016/S0926-5805(01)00056-5
3
Aamodt, A. and Plaza, E. "Case based reasoning: foundational issues, methodological variations and system approaches", Artificial intelligence communication, 7, 39-59, 1994.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £105 +P&P)