Home // International Journal On Advances in Systems and Measurements, volume 11, numbers 1 and 2, 2018 // View article

Univariate Modeling of the Timings and Costs of Unknown Future Project Streams: A Case Study

Authors:
Alireza Shojaei
Ian Flood

Keywords: Project Portfolio Management; Stochastic Forecasting; Time Series Modeling; Strategic Planning; Uncertainty

Abstract:
Providing a practical and comprehensive methodology to facilitate management and coordination of multiple projects in a company’s portfolio is a challenging task. Historically, the focus of research has been limited to the selection and prioritization of the set of known projects, current and near future. It is argued that existing portfolio planning models can be improved by adding a stochastic generator of project streams that extends the portfolio and strategic planning horizon to include future unknown projects. The study both identifies the historical factors in the market that are strong predictors of the profile of future project streams and evaluates alternative modeling approaches to the problem. The outputs from the generator are those parameters most critical to a company, namely the occurrence and letting date of a project, its expected duration, and its expected cost. A case study of design-bid-build highway construction projects let by the Florida Department of Transportation (FDOT) is presented for developing, validating and testing the concept of a project stream generator. The results show that FDOT’s future projects can be stochastically forecasted by using historical data and autoregressive moving average modeling along with sampling from representative distributions of cost and durations of FDOT’s projects.

Pages: 36 to 46

Copyright: Copyright (c) to authors, 2018. Used with permission.

Publication date: June 30, 2018

Published in: journal

ISSN: 1942-261x