I-Corps: Translation Potential of a Predictive Risk Analysis Platform for Large-Scale Projects with Complex Operating Environments

University Of Southern California, Los Angeles CA

Investigators

Abstract

This I-Corps project investigates the commercial potential of a risk analysis software platform to better predict sources of risk in complex operational environments, such as large-scale infrastructure, mining, or energy projects. Through the analysis of multiple, real-time data sources from project stakeholders, the platform builds continuously updated risk models to identify potential causes of risk and provides recommendations for mitigating those risks. Unlike traditional methods that rely on static assessments or periodic data entry, this approach emphasizes continuous monitoring and early detection. By better forecasting risk factors and identifying preventive measures, the platform helps teams operating in complex environments make smarter decisions and avoid problems that could delay or stop their work. Greater risk prevention measures could ultimately result in faster implementation times of large-scale projects, increased efficiency in high-complexity operations and providing greater prosperity across geographic regions in the U.S. This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on a comprehensive risk analysis platform that includes advances in natural language processing, causal inference, dynamic knowledge graph modeling, and geospatial analysis. These components are integrated into a unified system that ingests and interprets real-time data to generate timely, actionable strategies. The system includes an interactive interface that allows teams to pose hypothetical scenarios, such as policy changes or project delays, and receive predictions about how these changes could impact outcomes. The model’s outputs are based on both real-time observations and patterns extracted from historical data. This approach supports proactive planning by providing early signs of emerging risks and offering evidence-based risk mitigation, transference or avoidance strategies. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.