About me

Brandon M. Greenwell

Hello and welcome to IS4010!

My name is Brandon Greenwell, and I’ll be your instructor for this course.

I am a professor in the department of operations, business analytics, and information systems (OBAIS) here in the Lindner College of Business.

Welcome everyone. I’m excited to have you here for what I think is one of the most interesting and rapidly evolving topics in tech today. My goal is to make this a practical, hands-on course that prepares you for the future of software development.

My research focus

My academic work centers on interpretable machine learning and explainable AI (XAI).

• What does that mean? I build tools and methods to help us understand why complex machine learning models make the predictions they do.
• Instead of treating AI as a “black box,” my work aims to open it up and make it more transparent, trustworthy, and useful.
• This is crucial for fairness, debugging, and building reliable systems.

My passion is really about peeking inside the black box of AI. When a model makes a decision—whether it’s for a loan application, a medical diagnosis, or a simple business forecast—I believe it’s critical that we can ask “why?” and get a meaningful answer. This field is often called XAI, or explainable AI.

From research to practice

I believe in turning research into practical, open-source tools that everyone can use.

You can find most of my work on GitHub (github.com/bgreenwell), where I maintain several popular R packages for machine learning and data science.

Some examples include:

• vip: For constructing variable importance plots.
• pdp: For building partial dependence plots.
• fastshap: For computing fast, approximate Shapley values for feature contribution.

I’m a firm believer that academic work shouldn’t just live in papers. It should become real software that people can use to solve real problems. That’s why I spend a lot of my time on GitHub, building and maintaining open-source packages. Many of these are tools that help other data scientists and developers implement the interpretability methods I just mentioned.

Connecting my work to this course

You might notice my public work is mostly in R, but this course focuses on Python and Rust. Why?

• The principles are universal. The concepts of programming, data structures, logic, and even AI are not tied to one language.
• The future is multi-lingual. A modern developer rarely uses just one tool. The most valuable skill you can learn is how to learn a new language or framework efficiently.
• This is where AI assistants shine. We are in a new era where tools like Copilot and Gemini make learning new languages easier than ever before. We will embrace that head-on.

So, you’ll see a lot of the R language on my GitHub. But this course is in Python and Rust. I designed it this way for a very specific reason. The fundamental principles we’ll cover—from OOP to error handling—are universal. More importantly, learning to be adaptable is the most critical skill you can have. We’re going to use the AI tools in this course to help us bridge that gap and learn new technologies faster, just like you will have to do in your careers.

Let’s have a great semester

My goal is to make this a collaborative and supportive environment.

• Ask questions in the Teams channel.
• Come to office hours.
• Experiment, build things, and don’t be afraid to break stuff.

I’m looking forward to seeing what you all create!