Megaproject data quality assessment and performance predicting using Machine Learning
Research Group Activities
Project Praxis is a research group within WMG. At the root of any transformation lies a project which is developing a new approach to researching projects in organisations.
Whether you are introducing a new product, digitising a business or constructing a megaproject, you need to be adept in the fundamental skills involved in project, programme and portfolio delivery. Praxis is a term created by the Ancient Greeks to describe the way in which theoretical knowledge becomes real experience. The Project Praxis group prides itself on helping organisations turn the best of project research into the best of project practice.
Project Description
Megaprojects are extremely complex infrastructure projects costing more than ~£1bn that deliver society‚ energy, water, transport and even cultural needs. Megaproject delivery challenges demand novel techniques to diagnose current situations and predict project performance. As a powerful tool to extract vast amounts of information from data, machine learning (ML) techniques could benefit the decision-making process, transform the way people manage projects, and help improve project delivery performance. These outcomes could be applied to real-world megaproject datafication, with the prospect of saving billions of pounds in delivery costs per annum.
The aim of this project is to establish if‚ and how‚ to use ML techniques to predict megaproject performance. The "if" involves developing a data quality assessment pipeline to evaluate the feasibility of ML adoption in megaprojects. And the "how" will provide effective real project data processing approaches to that demonstrate the best-performing ML models. These predictions will be used in real-life decision-making to improve megaproject performance. This part of research will involve three main stages:
Optimization- This work also involves comparing and narrowing the range of potential ML algorithms options used in project performance prediction.
Simulation-This involves building ML models as well as training and testing the solution before applying it.
Probability and statistics - This includes the use of ML algorithms and real-world data to discover useful insights and risks, make reliable predictions, and test possible solutions.
The project will involve working with a variety of blue-chip companies, UK Government departments and full-stack developers to understand how they can use AI to predict and improve project delivery performance. The work will be wide-ranging in scope and allow the intern to work to his or her strengths. Interns will be involved in supporting focus groups and workshops with companies to understand their data analytic needs, to assist in encapsulating findings in research reports and, if they wish, to be involved in the creation of machine learning prototype prediction tools.
This project would provide the intern with an excellent opportunity to work with a variety of organisations to increase their understanding of project delivery and to develop highly desirable skills in data analytics.
Required Skills
Python/R
Apply for this Project
If you wish to apply for this project, fill in the form below including uploading your CV and personal statement, explaining why you want to do this particular internship project. Attachments must be in PDF format.
