How to Win Second Place at a Machine Learning Hackathon When You Don't Know What Machine Learning Is and Can't Code.
The morning of Friday the 13th I showed up to the Twin Cities Startup Week Hackathon without a team, no idea how machine learning worked, and most importantly- I can’t code. So what was I doing there? I figured I’d find a team of developers that could use a user experience designer. To my surprise, most of the teams already had designers on them. What's a person to do?
So my choices were:
• Join a team and be redundant
• Join a team with a project I didn’t find exciting.
• Sit with the Nexosis folks sponsoring the event and learn more about their machine learning API.
I chose the latter. At first, it felt like that old school cafeteria conundrum and I was stuck sitting with the teachers. Over the next few hours, they taught me about their API and encouraged me to search through datasets at kaggle.com.
The goal of the Hackathon was to create something for the better good. My first idea was to make an app that would take in the top ways Americans fear they’re going to die (terrorism, mass shooting, shark attacks) and compare them to how people are really dying (heart attacks, cancer, car accidents) and then predict the exact way you’re going to die. A “What should I really worry about?” app. The Nexosis team explained to me how that would be outside the scope of a 7-hour hackathon, but in the future that would be a feature their API could handle easily. It would be best if I could come up with one dataset that would spit out an integer. So I pivoted to the CDC’s U.S. mortality dataset with the goal of the predicting life expectancy. This is when I had to confront my limitations.
I had an idea, but I was lacking the developer skills. I’m a UX Designer who’s created CMS websites, but whose programming knowledge starts at BASIC and ends after a couple hours on Codecademy learning CSS.
While staring blankly at my laptop a friendly Nexosis engineer walked up to my table and asked if there were any questions. I said yes, but that it was too stupid. “No such thing,” he smiled. “Okay," I gulped, "How are websites made?” ¯\_(ツ)_/¯ Maybe I should sneak out of here, I thought. Or maybe it's time for a Hail Mary.
I slacked out a message in the alumni developer channel at Prime Digital Academy (the bootcamp I attended.) to see if any developers could drop what they are doing and join me. Within 45 minutes Hogan McDonald arrived. We both attended Prime at the same time. He was in the developer cohort and I was in the UX cohort. He had recently completed an online machine learning certification course. With less than 3 hours on the clock, he put together a backend that interacted with the Nexosis API. It simultaneously told Nexosis how to interpret our data (Living in a server farm in Virginia.) and how to access it from AWS. Next, he built an interface and I cleaned the Mortality dataset. At one point the Nexosis staff informed us that Hogan was the first outside developer to access their API using Node.JS. When time was up we had a working web application with a simple interface. It asked for your gender, marital status, and level of education. Then using machine learning it predicted the date and time of your death. The hackathon judges awarded us with second place trophies (We tied with another team.) and Nexosis swag.
I think that the communication skills we learned at Prime made us stand out during our presentation to the judges. Especially when dealing with a potentially morbid subject. We were able to explain the user experience with and without our website and how it will improve. As well as how we built our web app and our stretch goals.
Before the hackathon, I would have thought it’d take a team of developers weeks to do what we did in a few hours. As a designer, this opens a whole world of innovative solutions to me. I have a new tool! Our webpage is called, "I Know When You're Going to Die." and if you click the link you can find out for yourself.
Here is the repo with our code.
Here is a link to the Nexosis machine learning API, you can try it out for free.
Shout out to the winners of the Twin Cities Startup Hackathon, Default Value, with their bad day predicting text messaging self-care program.
Top Photo by Alex Kotliarskyi on Unsplash