Integrating machine learning and network analytics to model project cost, time and quality performance

This study aims to connect project management, network science and machine learning in an accessible overview applied to a real original dataset. Based on an initial literature review of applicable project performance measures and attributes, relevant project data were collected through an online survey. The information was split into three categories, including the basic project measures (five attributes), project stakeholder network measures (seven attributes), and project complexity measures (seven attributes). In total, 70 responses were collected, and five machine learning approaches (i.e. support vector machine, logistic regression, k-nearest neighbour, random forest and extreme gradient boosting) were applied to model the relationships between project attributes, networks and the Iron Triangle of project cost, time and quality. The results confirm the expected trends affecting project performance and provide an example for the discussion of the applicability of integrated machine learning and network analytics approaches to modelling project performance. The article demonstrates in an accessible way a real case of integration of machine learning, network science and project management and suggests avenues for further research and applications in practice.

Automated summary

This study connects project management, network science, and machine learning by applying them to a real dataset. Relevant project data was collected through an online survey and categorized into three groups. Five machine learning approaches were used to model the relationships between project attributes, networks, and the Iron Triangle of project cost, time, and quality. The results confirm expected trends and provide an example for the applicability of integrated machine learning and network analytics to project performance modeling.