The association analysis for risk evaluation of significant delay occurrence in the completion date of construction project
Hubert Jerzy Anysz , B. Buczkowski
AbstractIt is widely known that a construction project can be described as a success if it is completed on time and without cost overrun. As the strong correlation between delay in completion date of construction projects and cost overruns exists, it is necessary to manage the risk of a delay from the very beginning: even before the start of works execution. The data concerning 139 construction contracts of the highway sections already completed, as well as their completion dates, were collected. The twelve types of data were chosen based on the criterion of time of appearance: they should be known before the start of construction works. Most of the contracts’ properties have continuous values, and these had to be converted to the binary values. With the use of the association analysis, it is possible to find the combination of properties of the construction contracts that have produced significant delays in completion date in large part of analysed and already completed contracts. For this purpose, appropriate software has been created. This paper will comprise the software approach to the problem as well as the result of the analysis, as it is based on real data completed. Getting the information on which combination of construction contract properties can cause a significant delay in completion date of the contract, the client can make decisions leading to avoiding risk, i.e. providing better circumstances for project success.
|Journal series||International Journal of Environmental Science and Technology, ISSN 1735-1472, (A 30 pkt)|
|Publication size in sheets||0.5|
|Keywords in English||Association analysis, Rule finding, Risk estimation, Construction project delays|
|ASJC Classification||; ;|
|Score|| = 30.0, ArticleFromJournal|
= 30.0, ArticleFromJournal
|Publication indicators||: 2017 = 0.904; : 2017 = 2.037 (2) - 2017=2.152 (5)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.