We will use probabilistic modeling and stochastic simulation as tools for guiding risk-informed decisions in complex environments with material uncertainty about the future. The first part of the course will focus on quantifying various measures of equity return risk using historical data. We then focus on forecasting distributions of returns using both parametric and nonparametric approaches. Forecasting requires a 'model' so we assess parameter and model risk. This part of the course emphasizes developing models linked to financial data and assessing model performance.

The second part of the course uses stochastic simulation cases to practice deriving robust strategies for the decisions that risk managers must make in real time, including managing liquidity risk, market risk, crash risk, and real economy risks. We use the RIT market simulator platform (analogous to using a flight simulator); decision models for each RIT case are linked to data from the simulated market, that is, data generated by the class participants. The markets aggregate participants' decisions and provide immediate feedback, allowing you to adapt strategies given the range of potential outcomes experienced in the multiple replications of the case.