Machine learning in project schedule creation: a systematic literature review

Abstract

Addressing the growing demand for autonomous project scheduling, this study explores the use of machine learning (ML) for project schedule creation. It is a well-known fact that ML surpasses human capabilities in analyzing extensive data. For this reason, ML is a promising domain for organizations that gather project experience. However, the current ML adoption in project management remains limited, lacking systematic studies demonstrating its potential. This is the first study that presents a comprehensive review of the current state of knowledge in the project schedule creation area. We summarize the ML techniques used in each schedule creation area and investigate their demonstrated potential in improving schedule creation processes. Moreover, we analyze in which industries such methods are most often used. Furthermore, we explore anticipated advancements, highlight potential benefits, and address current limitations of ML applications in the domain of schedule creation. We also uncover key gaps in research, discuss related challenges, and emerging trends. Additionally, we elaborate on practical implementation strategies for ML-based schedule creation, emphasizing that while ML has the potential to enhance project scheduling, full automation is unlikely in the near future. Instead, automating specific subprocesses appears to be the most practical approach for integrating ML into schedule creation at this stage.