Kathryn Caggiano received a B.S. in Mathematics from the College of William and Mary in 1990 and a Ph.D. in Operations Research from Cornell University in 1998. Prior to returning to Cornell in 2007, Professor Caggiano was an Assistant Professor of Operations and Information Management in the School of Business at the University of Wisconsin-Madison. Outside of academia, she worked for several years in technology and supply chain consulting with Price Waterhouse and PeopleSoft Supply Chain Solutions. In her current role as Director of Master of Engineering Studies, Professor Caggiano is actively involved in the professional preparation and development of ORIE students at both the undergraduate and graduate levels. Under her leadership, the ORIE MEng program was selected as a finalist for the 2012 UPS George D. Smith Prize, INFORMS’s flagship award for the outstanding practical preparation of OR students.
If you've ever been asked a question like “What is the projected sales revenue for the next quarter?” or “When will your major development project be complete?” then you know a common answer is “It depends.” While most of the decisions or projections we make include some level of uncertainty, we often fail to account for this uncertainty, resulting in suboptimal outcomes.
In this course, you will explore how to build robust evaluation models in Excel and incorporate the impact of uncertainty. As you work through this course, you will get hands-on practice identifying situations where using fixed “average” input values can lead to poor estimates and decisions. In Excel modeling, when we use a single fixed number in all scenarios to represent an uncertain value to be revealed in the future, the actual outcome of that value could substantially impact the model metrics and resulting decisions.
A better approach, which you will practice in this course, is to build robust models that allow a user to account for those different outcomes and provide visibility to the potential consequences and tradeoffs. More specifically, you will develop an Excel-based framework for generating random values from several probability distributions that you can use to build simulation models to help understand and manage system performance. At the end of this course, you will have a variety of tools and strategies to develop models that can account for uncertainty, enabling you to make better-informed decisions.
You are required to have completed the following courses or have equivalent experience before taking this course:
- Making Data Usable
- Creating Effective Data-Driven Dashboards
Key Course Takeaways
- Recognize why uncertainty matters and incorporate an uncertain factor into a model
- Model and simulate random values from the discrete, binomial, Poisson, and normal distributions
- Use simulation to assess system performance and conduct sensitivity analyses to stress-test decisions
How It Works
Who Should Enroll
- Finance professionals
- Data analysts
- Data scientists
- Business analysts
- Managers and executives
- Students who need in-depth Excel knowledge