Who is This Course For?

TL;DR

Well, first of all, the answer will be different for different times.

At the time of writing this page, this course is designed for you if you are interested in hands-on experience in making data-driven decisions as a course project. This course is designed to help you learn how to structure your project, how to build an optimization model, how to prepare data, and how to use the model to make an informed decision and present it to your audience.

By no means, this course is designed for you if you are looking for a course that will teach you the theory of data analytics or theory of operations research. This course is not for you if you are looking for a course that will teach you how to use data analytics tools such as Python, R, or Julia from scratch. Although, you will learn how to use these tools in this course. The focus of this course is to help you learn how to apply prescriptive analytics to solve problems in your own context.

Lessons Learned from Past Semesters

That being said, my own reflection throughout this course is that many students are not familiar with the tools and techniques that we will be using in this course early on. While the notion of “analytics” is not new to them, the notion of “prescriptive analytics” is. Most of wrong project directions are due to the lack of familiarity with the scope of the prescriptive analytics.

To be clear, we will not be focusing on making predictions for new data, nor making insightul visualizations for high-dimensional features, especially in the second half of the course. We will be focusing on making decisions based on data, which might use some of these techniques. We will most often be using tools such as AutoML to automate the process of building a model and handwave the process of data preparation and model training (see for instance optimization with a surrogate objective in the Model Examples resource section).

What I have come to realize is that we will need to revisit how to read the “summation” operator in the context of compact formula representation and how to write them. This is often the first thing that students struggle with when they are trying to read chapters from the book and write math expressions in Pyomo or similar modeling tools. This is absolutely fine, and we will have a few short assignments to help you get familiar with this.

What You Need to Succeed in This Course

A lot of practice. Again, this is a course that is designed for you to learn by doing. You will be required to do a lot of practice on your own, and you will be required to do a lot of practice in class. You will be required to do a lot of practice in the project.

The good news is that you will be working in a team, and you will have a lot of support from your peers. You will also have a lot of support from me and my team, as the instructor.

You Decide Which Aspect You Want to Focus On

As of 2025, I will be working on setting up different tracks for this course, depending on your interest. The tracks will be as follows:

• Track 1: The track that is designed for those who are interested in hands-on coding and modeling experience. This track will be focused on helping you learn how to use Python, Pyomo, and other tools to build models and solve them given a data and an objective. You will be evaluated based on your ability to build a useful model, solve it, and verify the solution. You will be required to build a model that can be prototyped rapidly (for instance using Gradio or Streamlit).

• Track 2: The track is for you if you want more data processing and visualization experience. You will be provided with a model and solver and your job is to find and process real-world data from your organization and visualize the results that your supervisor can comprehend and use to make decisions. Tools such as Pandas, Matplotlib, Seaborn, and Plotly will be highly useful. You might need to extract results from Pyomo models to feed into these tools. You will be evaluated based on your ability to collect, present, and process data as well as visualize and validate the results.

• Track 3: This track is for those who are interested in the supervisory and project management side. You will be required to work with your team and ensure their well-being and progress. You will also be required to strategize how to deal with risks and uncertainties in the project. Tools such as GitHub project management, Trello, and Google Suite (Google Docs, Sheets, Slides, Calendar) might be useful. You will be evaluated based on the delivery of your project (presentation, report, and code), the reviews from your team members (peer review), and the insights you provide as a supervisor (managerial insights and team review).

You will be required to choose one of the tracks above. If you are not sure which track to choose, you can choose the track that you are most interested in and adjust before the midterm. The tracks you choose will define the way you will be evaluated in this course.