Assessing the impact of claims on construction project performance using machine learning techniques

This study aims to assess the impact of claims on construction project performance and evaluate the effectiveness of change management strategies. Using a quantitative approach, data was collected via a detailed questionnaire distributed to industry professionals, including consultants, contractors, project managers, and owners. The data was rigorously cleaned and analyzed using the Light GBM model optimized with the Locust Swarm Algorithm. Key findings reveal that delay claims increase project timelines by 20% and costs by 15%. Effective change management strategies significantly mitigate these impacts, with structured frameworks improving accuracy by 25%, precision by 20%, recall by 22%, and F1 scores by 23%. The optimized machine learning model showed a 15% improvement in accuracy and a 12% improvement in precision over non-optimized models. This study contributes to construction management by highlighting the critical role of robust change management in mitigating claim impacts and enhancing project performance. It also demonstrates the transformative potential of AI and ML in civil engineering, facilitating data-driven decision-making, optimizing resource allocation, and improving overall project outcomes.