Predictive Monitoring of Resources Consumption in Project Management

Abstract

Monitoring resource consumption is a critical concern in project management, as it can significantly impact a project’s success. Project management experts often rely on their experience and heuristics to navigate management challenges and adhere to predefined constraints. However, relying solely on experts’ judgments can lead to disagreements and biases, hindering consensus and optimal decision-making. In this context, a data-driven approach leverages accumulated data and machine learning to develop unbiased models suitable for automation, including prediction, classification, anomaly detection, and more. In this paper, we propose a method for predicting resource consumption, encompassing expected, unplanned, and surpassing tasks. Our experiments demonstrate strong predictive performance using real-world datasets across various task types.