Answers are grounded in this paper and cite their sources.
Metro rail projects are naturally complex because of their large size, technical demands, different stakeholders, and government rules. These challenges can affect how well a project performs in terms of time, cost, scope, quality, sustainability, and reliability. But current project management methods often don’t have tools that can predict how these complexity factors will interact and affect the project. This study tries to fill that gap by building a machine learning (ML) model that looks at how project complexity affects metro rail project performance. A two-stage methodology was adopted, where semi-structured interviews with 30 professionals were used to identify project complexity factors, followed by machine learning model development and validation using 278 valid survey responses collected from metro rail stakeholders. The model uses three ML techniques – Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT)- and is based on survey data from 278 metro rail project stakeholders working on major metro rail projects in India. The results show that the model demonstrates strong predictive performance for time and cost, moderate performance for scope, quality, and sustainability, and comparatively weaker performance for reliability. This study offers a practical tool that project teams can use to better understand project risks and improve planning and decision-making in large infrastructure projects.
No takes yet. Share an insight, caveat, or question.
Dara et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: