• Mr. Syed Ateeb Isfar
• Prof. H.B Dahake

Construction contracts are prepared before all project conditions and financial consequences are fully known. Design errors, unclear contractual responsibilities, inaccurate estimates, scope changes, resource delays and payment problems may generate additional costs or claims. Conventional risk allowances can be useful, but a fixed percentage or an experience-based judgement may not adequately reflect the changing exposure of an individual project. This study examines how professional risk assessment can be linked with a proposed dynamic risk-pricing framework for construction contracts. A structured questionnaire was analysed using 125 valid responses from construction professionals. Descriptive statistics, mean scores and the Relative Importance Index (RII) were used to rank risks across three dimensions: frequency, severity and perceived financial impact. Design errors and incomplete drawings received the highest combined risk-priority score (RII = 0.654), followed by unclear contract conditions and allocation of responsibilities (0.643) and inaccurate cost estimation (0.633). The survey also found that 64.0% of respondents considered fixed allowances insufficiently responsive to changing conditions, while 64.0% supported reviewing allowances when project conditions change. Published studies on construction claims and predictive modelling were reviewed to identify suitable data structures and validation practices. The resulting framework connects survey-based risk prioritisation, project information, historical claims records, conditional machine-learning analysis, contractual risk allocation and professional review. Importantly, the questionnaire dataset did not contain claim-level historical records; therefore, no machine-learning model was trained or validated in this study. The contribution is a data-informed framework and a transparent calculation structure whose predictive component requires future testing on suitable historical claims data.

Construction contracts; dynamic risk pricing; construction claims; Relative Importance Index; risk allowance; historical claims data; machine learning

"Framework For Dynamic Risk Pricing In Construction Contracts Using Machine Learning on Historical Claims Data ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 10, page no.b576-b590, October-2026, Available :http://www.jetir.org/papers/JETIR2610160.pdf

"Framework For Dynamic Risk Pricing In Construction Contracts Using Machine Learning on Historical Claims Data ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 10, page no. ppb576-b590, October-2026, Available at : http://www.jetir.org/papers/JETIR2610160.pdf