UBC MDS

For the past three months, I was on a team of UBC Master of Data Science (MDS) students working on our MDS capstone project. Our team developed a data science product to help the course creators on the Thinkific e-learning platform to improve their online courses. Unsurprisingly, working on the improvement of online learning was a great learning experience for ourselves. Therefore, to share some of my experiences, and as a reminder to my future self, in this post I will summarize the six most important lessons I learned during the project. But first, to give some context, I’ll quickly describe the client and the project.

In my second year of medical school, I decided to open an unfamiliar email entitled “UBC Centennial Symposium on Health Informatics”. What was Health Informatics? I had no idea, but I intended to find out. The symposium featured the UK’s National Health Service (NHS) and showcased their use of large population datasets. I was impressed with how the NHS uses data to improve care. I went into medicine because of a personal desire to help people one-on-one; applying data science to healthcare seemed to provide the opportunity to positively impact millions at a time, in addition to one at a time.

This is the first in what will hopefully become a series of posts on our curriculum for the Master of Data Science (MDS) program at UBC. Our program is structured as six four-week blocks, each containing four mini-courses, for a total of 24 mini-courses. Each of these mini-courses is about one third the size of a regular university course. The image below summarizes our current schedule:

(For more details on each of these courses, see here.)

After eight months of coursework, the UBC Master of Data Science (MDS) program concludes with a 2-month Capstone project. We partnered with Ido Roll from UBC’s Centre for Teaching, Learning and Technology (CTLT) to analyze data from UBC’s massive open online courses (MOOCs). UBC offers dozens of MOOCs to thousands of students through the edX platform. Unlike in-person classes, in a MOOC the instructor cannot observe student engagement directly. Instead, they must infer student engagement from recorded events (for example, a student pausing a video). A single course can involve millions of events in its lifetime, which means there was lots of data for us to look through. Our task was to build a dashboard to help MOOC instructors answer the following questions:

One of the most rewarding aspects of working on the UBC Master of Data Science program has been the close collaboration between my home department, computer science, and the statistics department here at UBC. The collaboration has also come with a challenge, though: the two communities often use different words to mean the same thing. A prime example would be the word “bias” – it is hard to get an unbiased opinion on what this word means! Over the last couple of years I recorded these discrepancies in a “statistics / machine learning dictionary” and also expanded the scope of the document to include general terminology issues that arise in data science. The current version of the document can be found here. As one highlight, I’ve found that all of the following terms can refer to the same thing: predictors, features, inputs, explanatory variables, regressors, covariates, and independent variables! In general, terminology is a tricky business because there aren’t always objective truths and yet people tend to feel quite passionate about it.