Resource-Based Time and Cost Prediction in Project Networks: From Statistical Modeling to Graph Neural Networks

TL;DR

This paper introduces a graph neural network-based framework for predicting project duration and cost, outperforming traditional methods by capturing complex task-resource relationships in project networks.

Contribution

It presents a novel resource-based GNN model that models project activities and resources as a heterogeneous graph, improving prediction accuracy and interpretability.

Findings

Achieves 23-31% reduction in mean absolute error compared to traditional methods.

Improves R2 from 0.78 to 0.91 on complex project datasets.

Provides interpretable embeddings for resource bottlenecks.

Abstract

Accurate prediction of project duration and cost remains one of the most challenging aspects of project management, particularly in resource-constrained and interdependent task networks. Traditional analytical techniques such as the Critical Path Method (CPM) and Program Evaluation and Review Technique (PERT) rely on simplified and often static assumptions regarding task interdependencies and resource performance. This study proposes a novel resource-based predictive framework that integrates network representations of project activities with graph neural networks (GNNs) to capture structural and contextual relationships among tasks, resources, and time-cost dynamics. The model represents the project as a heterogeneous activity-resource graph in which nodes denote activities and resources, and edges encode temporal and resource dependencies. We evaluate multiple learning paradigms, including GraphSAGE and Temporal Graph Networks, on both synthetic and benchmark project datasets. Experimental results show that the proposed GNN framework achieves an average 23 to 31 percent reduction in mean absolute error compared to traditional regression and tree-based methods, while improving the coefficient of determination R2 from approximately 0.78 to 0.91 for large and complex project networks. Furthermore, the learned embeddings provide interpretable insights into resource bottlenecks and critical dependencies, enabling more explainable and adaptive scheduling decisions.