About the dsTRAIn

The purpose of the Data Science TRAIn Lab is to expose Macalester undergraduate students to the interdisciplinary field of Data Science by encouraging students to:

  • (T)ry

    Try new data science and machine learning techniques on the datasets and questions of interest to them


  • (R)ead

    Read at least one paper in data science and machine learning each week


  • (A)sk

    Ask questions about data science and machine learning as well as questions about data from a variety of domains


  • (In)corporate

    Incorporate a variety of expertise to ask interesting questions using data science and machine learning techniques, and to incorporate lab experiences into the broader Macalester education and experiences


The Principal Investigator for the dsTRAIn lab is Katherine M. Kinnaird, of the MSCS Department at Macalester College

A Focus on Data

In our current age of personal computing devices, social media profiles, high-resolution medical scans, and smart phones, there is a wealth of data for every domain imaginable. The next step is to understand this data to help inform our world and our choices. For example, can we determine the next big song in America by looking at music listeners’ current playlists? What about the big song for 2020? To answer these questions and those like it, we need to better understand what data like a playlist may tell us and what information could be lacking. We need to investigate if it is possible to get data that fills in any gaps in our information. The process of answering questions involving lots of data require both experts in the domain that our data comes from as well as experts in data science and machine learning. This lab seeks to have all kinds of experts will differing levels of expertise, who all have an interest in data science or the domains that have questions that data science can help address.

Currently on dsTRAIn

  • Current Projects

    From equities and education, to solar farms and disease migrates, dsTRAIn-ers are investigating a range of questions using data science and machine learning. Check out what projects we're currently working on.
  • Current dsTRAIn-ers

    The Data Science TRAIn Lab is comprised of enthusiastic data scientists and machine learners who are biology, political science majors, mathematics, and CS majors. Meet the current members of dsTRAIn.
  • Start Your Own TRAIn Lab

    Are you interested in our method and mission? Learn more about the TRAIn method and view resources about starting your own TRAIn lab. We would love to collaborate with you and help you start your own TRAIn.
  • dsTRAIn in the World

    As dsTRAIn projects produce results, we will be giving talks and posters on our work. Check out what projects page to see what presentations we've made.