Examination the Usefulness of Selected Classification Methods in the Pre- Qualification of Construction Contractors

摘要

For most of projects, including major infrastructure enterprises a key success factor is an appropriately selected general contractor. In addition to technical and organizational criteria the assessment of its financial capacity is strongly important to provide liquidity to the cash flows of the project. Unfortunately, the practical experience of the construction market during the economic downturn shows that many projects have been delayed or suspended as a result of the bankruptcy of general contractors. The purpose of this paper is to present the results of studies on the use of Partial Least Square, Fisher Linear Discriminant, Support Vector Machine methods, and the authors' proprietary approach to the Extraction by Applying Weighted Criterion of Difference Scatter Matrices (EWCDSM) for the pre-qualification of potential contractors. The study included an ex post evaluation of selected large construction companies, operated in Poland by reference the fact of their bankruptcy or maintain the market to historical financial data for the prior year period. Then, for the same set of data the authors performed the identification of companies at risk of bankruptcy. The results obtained are confronted with the actual condition of the surveyed companies. Proposed operating models have been validated on publicly available financial data of construction companies listed on the Polish Stock Exchange.