RISK ANALYTICS
Develop a toolbox for modeling, communicating, and managing risk and uncertainty in business applications. Emphasis on the notation of probabilistic forecasting and introduces a predictive modeling framework that integrate modern machine learning methods with distribution-based regression models. Topics include heavy-tailed regression, count data regression, survival data analysis, feature engineering using neural networks and natural language processing, among others.
Topics
- heavy-tailed regression
- count data regression
- survival data analysis
- feature engineering using neural networks and natural language processing
- among others
Topics explicitly listed in official catalogue description
Prerequisites & course information
Requisites: ( ACT SCI 640 , GEN BUS 656 , STAT 333 , or 340 ), or declared in undergraduate Business Exchange program Course Designation: Core GenEd - Mathematics & Quantitative Reasoning Level - Advanced L&S Credit - L&S Liberal Arts and Science Repeatable for Credit: No Last Taught: Spring 2026 Learning Outcomes: 1. Articulate the difference between point prediction and probabilistic prediction in a business context. Audience: Undergraduate 2. Build predictive models for the purpose of probabilistic forecasting in business applications. Audience: Undergraduate 3. Select appropriate modeling strategy and evaluate performance of the models in a given business context. Audience: Undergraduate 4. Perform feature engineering to incorporate complex pattern and unstructured data into the predictive model development for business applications. Audience: Undergraduate 5. Interpret the prediction outcome and communicate results to non-technical business audiences Audience: Undergraduate Learning Outcomes: 1. Articulate the difference between point prediction and probabilistic prediction in a business context. Audience: Undergraduate 2. Build predictive models for the purpose of probabilistic forecasting in business applications. Audience: Undergraduate 3. Select appropriate modeling strategy and evaluate performance of the models in a given business context. Audience: Undergraduate 4. Perform feature engineering to incorporate complex pattern and unstructured data into the predictive model development for business applications. Audience: Undergraduate 5. Interpret the prediction outcome and communicate results to non-technical business audiences Audience: Undergraduate
Sources
- Course catalogue ↗2026-2027