Research on Construction Projects

This is a solution of Research on Construction Projects in which we discuss Construction Projects IT strategy can help your company cope with aging systems and limited resources that can lead to fragmented IT solutions.


Construction projects are highly complex and are therefore prone to failures. Project management methodologies can only minimise risk of failure but cannot guarantee successful completion. However, early prediction of future project trajectory can provide sufficient early warnings and sufficient time to respond in case significant deviations from the plans are predicted. Such capability would require the rapid assessment of project documentation and reports and the ability to infer potential future failures from unstructured information, analysis of emotion and sentiment in the writing style of those reports. Such capability is currently not routinely available.

Research on Construction Projects
Research on Construction Projects

Aim & Objectives

The research aims to develop a predictive early warning methodology for project failure prediction by analyzing unstructured project documentation such as project report. Machine learning will be employed to extract from such sources actionable information to compare against project plans and key performance indicators. The research will proceed with the following objectives:

Develop a project progress assessment methodology encompassing factors affecting project performance.

  1. Develop a methodology and algorithmic approaches for the analysis of unstructured project documentation and extractions of key actionable information to allow inference of actual project progress rapidly.
  2. Develop a prototype tool and tune against a series of case studies from literature.
  3. Conduct an empirical study demonstrating the approach.

    Project Challenges

Some implementation issues been taken into consideration including these following questions:

  • What are the most important EWSs of failures specific to project performance in construction industry?
  • What are the causes of the EWSs specific projects performance in construction industry?
  • When the project performance is affected by different factors?
  • How to measure datasets; organizational and persons factors?
  1. Methodology

A mixed methodology will be used and will include both qualitative and quantitative methods. Specifically, a mixture of data from both the literature and real life will be employed to demonstrate this approach. Therefore, the project is divided into phases, and each one of these phases has objectives.

(1) Analytical Phase:

An advanced research will be conducted in order to identify the early warnings behind the project failures that occur in construction projects. The early warnings and parameters identified in each of its related papers will then be recorded (TABLE 1), in order to use later on during the development stage.

Table 1 shows a primary list of early warnings and a description of issues analyzed and referenced from different sources.

Early Warnings Early Warnings Issue References
lack  of making purchases The style of delays to make purchases EWS, Ilmari O. Nikander, 2000 [1]
Lack of materials on site shortage of materials delaying the work
Lack of resources Shortage of staff, poor mix of responsibility Kappelman et IT projects 2006 [6]
lack of  keen commitment to the project milestone andscops Delivering the promised project scope (e.g. freezing action, repetitive action) Kappelman et IT projects 2006 [6]
lack of project team required knowledge/skills Uncertainty regarding technical matters indicates ignorance McKeeman, 2001[2]

  (2) Model Phase:

The software project management system will be developed to read the data from unstructured documents and to detect the early warnings that are affecting or could affect the undergoing construction project.

The Text Mining technique will be used to represent all the tasks that, by analyzing large quantities of text documents, try to extract possibly useful information[5]. Results of the text mining process will be a collection of generic attributes that store information about a particular item of the unstructured document, that can be assisted by a classifier to generate knowledge about the subjects contained in these documents.

Naïve Bayes classification (Equations 1,2) will be employed to automatically build a classifier that will interpret the class/category which the object belongs to.   First, equation (1)  will be applied to calculate the probability of new entities by  observing the features of a set of documents that have previously been classified manually into the approach training set.  Hence, this approach relies on the existence of an initial corpus of early warnings, previously classified according to their relevance to a specific task in project plan[2]. Next, equation (2) will be applied to determine the probable threat or warnings that arise from parsing the item text.

Finally, an effectiveness evaluation will be applied by splitting the initial collection of documents into two sets; the Training set phase that will be used to create the approach model and the Test set phase that will be used for testing the approach model. Meeting minutes will have been selected for this evaluation, which store information about weekly progress meetings among project members; also referred to as case material .

A.     Equations

  • : The training set step algorithm has been used especially to calculate the probability of new entities from unstructured documents .

Where P(Wk|h) is the probability of observing data Wk given some attributes where approach early warnings holds (H),  n is how many times there are object occurrences in the approach trying set, (nk) is how many time the observed data occurred in the category of  the approach training set, |Vocabulary| is a unique attributes dictionary that has been identified according to its value to the subject.

  • : Naïve Bayes probabilistic with strong assumptions used to build the classifier .

hMAP refers to the maximum probability of early warnings, P (D|H) is the probability of the observed data given the approach of early warnings, and (pH) is the probability of the approaching early warnings.


In order to have a logical result we still need to develop the approach of the trying set, based on the existence of early warnings signs along with specific tasks in the project plan. These expected results from the system can allow construction projects to be assessed routinely and more promptly.


An initial list of early warnings has been collected to reveal the approach of the trying set (Corpus). Naïve Bayes has been successfully applied to calculate the probability of early warning signs for the first time. It appears to be a reasonable result so far. However, as mentioned in the results above, further development into the approach of the trying set is still needed in order to accomplish predictions as well as comparisons.

The project can potentially have significant impact to the construction industry globally by;

  • Establishing a unique methodology in project performance/failure prediction.
  • It’s a rapid performance analysis early warning system leveraging the wealth of information that is currently in unstructured formats and therefore not actionable by conventional software project management systems.
  • The research is still at year 3 of a PhD program but rapid progress is anticipated.{See more :-Research Proposal Assignment Help}


An empirical study will be conducted to demonstrate this approach. Two construction projects will be selected as case studies for this purpose. The first is 2013 construction project to observe how the identified early warning parameters affect the project plan that will be considered within the approach trying set. The second, is 2014 construction project to be observed in terms of accomplishing the project performance prediction. Although initial results are still not shown in this paper, rapid progress is anticipated.


Nikander, I. O., & Eloranta, E, (2001).“Project Management By Early Warnings”, International Journal of Project Management, 19, 385–399.

  • McKeeman, R, (2001). “Early Warning Signs of Project Failure”, Report for University of North Texas.
  • Nikander, I. O., & Eloranta, E,(2002). “Early Warnings: A phenomenon in project management”, Dissertation for Doctor of Science in Technology, Helsinki University of Technology, Espoo, Finland.
  • Soibelman, M.ASCE, H. Kim, (2002). “Data preparation process for construction knowledge generation through Knowledge Discovery in Databases”, Journal of Computing in Civil Engineering, 16 (1), pp. 39–48.
  • H. Caldas, L. Soibelman, (2003). “Automated Classification of Construction Project Documents”, Automation in Construction, 12, pp. 395–406.

Oz Assignment Help Australia provide assignment writing service based on case study requirements in affordable prices and we are providing most flexible online assignment writing help, so book your Assignment with us,  order now