Probabilistic forecasting of schedule performance using polynomial function

Using the progress S-curve as a tool for schedule performance forecasting for ongoing projects can improve the capability of project managers for making informed decisions. The objective of this paper is to provide a reliable estimating for the progress S-curve, which leads to better forecast for both the estimated duration at completion (EDAC) and the probability of success (POS) of the project. This study introduces a new probabilistic forecasting method, which is developed on the basis of the polynomial function as a curve fitting technique, for schedule performance control and for risk management of ongoing projects. The polynomial forecasting method (PFM) has been programmed in a graphical user interface (GUI) for Matlab (R2009a) and it can be applied to all types of projects. A comparative study reveals that the PFM provides much more accurate forecasts than those are generated from the conventional deterministic forecasting methods (CDFMs) and as accurate as the critical path method (CPM). Moreover, the PFM provides confidence bounds for predictions, which in turn can help the project managers to make better informed decisions in the form of corrective and/or preventive actions.