Embedded Files
Decision Intelligence for Complex Systems
Quantifying uncertainty. Pricing risk. Improving decisions.
We develop mathematical, computational, and AI-based methods to analyze risk and support better decisions in complex real-world systems. Our research focuses on understanding how uncertainty, operational variability, and system interactions affect performance, value, and decision outcomes.
By combining optimization, simulation, and data-driven modeling, we aim to translate complex risks into measurable insights and actionable decisions across a wide range of industrial applications.
Stochastic Optimization · Simulation & Digital Twins · Scientific Machine Learning · Decision AI
Research
Stochastic Optimization
Stochastic Programming · Robust Optimization · Simulation Optimization
Models for decision-making when uncertainty, risk, and operational variability matter.
Decision AI
LLM-enabled Decisions · Agentic Systems · Optimization Integration
AI systems that connect reasoning, models, and real-time information to decisions.
Scientific Machine Learning
Physics-informed Learning · Surrogate Modeling · Data–Model Integration
Data-driven models grounded in physical and mathematical knowledge for reliable prediction.
Simulation & Digital Twins
Operational Simulation · Physics-based Simulation · Digital Twins
Virtual environments for testing system behavior, scenarios, and operational decisions.
Application Domains
Energy & Climate Systems · Maritime, Port & Logistics Systems · Industrial & Supply Chain Systems
About
Risk Analytics Lab develops mathematical and computational methods for decision-making under uncertainty. We combine stochastic operations research, simulation, and artificial intelligence with real-world industrial data to solve complex operational problems.
At the core of our research is pricing uncertainty — quantifying how uncertainty changes the value of decisions, assets, and operations.
By translating uncertainty into measurable operational value, we develop decision models that improve the efficiency, resilience, and sustainability of real-world systems.
Contact
Collaboration & Opportunities
We welcome prospective students and research collaborations.
For inquiries, please contact our lab manager, Seongjun Lee (seongjun.lee@pusan.ac.kr).
Page updated
Google Sites
Report abuse