Contractual claims are among the most critical challenges in construction projects, often leading to cost overruns, time delays, and quality deterioration. This study aims to identify and analyze the key factors causing claims in water and wastewater projects in Mashhad using a combined data-driven and analytical approach. In the first stage, the influencing factors were identified through document review and expert interviews. Based on these results, a questionnaire was developed and the collected data were analyzed using SPSS software and the Friedman test to obtain an initial ranking of the claim-causing factors. In the next stage, a predictive model for claim occurrence was developed using the Random Forest algorithm. The results demonstrated that the model achieved an accuracy of 87%, indicating a high level of reliability. In addition, structural analysis based on Partial Least Squares Structural Equation Modeling (PLS-SEM) revealed that ambiguity in contract terms, unforeseen site conditions, and weak resource management are among the most influential causes of claims. Furthermore, the TOPSIS method was applied to grade and prioritize projects in order to support effective and structured decision-making. The results confirm that integrating data-driven approaches with decision support systems can significantly reduce disputes and costs, enhance transparency, strengthen trust between contractual parties, and improve the overall efficiency of construction projects. The proposed framework provides a practical foundation for the development of intelligent decision support systems aimed at proactive and systematic claim management in project-oriented organizations.