Mechanical engineering students take first place in this year’s 24-hour HackTheU Competition held in the Union earlier this month. HackTheU is what’s called an “invention marathon.”
Utah’s largest hackathon, HackTheU, attracted more than 450 college students across several states, who participated in the coding marathon. The participants competed for cash and prizes in one of the below themes. Additionally, HackTheU included keynote speakers and dozens of mentors from local and national companies.
Participants are given 24-hours to come up with a creation in one of the three given themes:
- Financial Technology (FinTech) – participants create new innovations in the field of Financial Technology such as utilize blockchain technology, or create new tools and apps to promote financial security for consumers, and so on.
- Community – participants contribute to the community by creating apps for a local animal shelter, school, neighborhood, or to help individuals with disabilities, and so on.
- Entrepreneurship – At the heart of Silicon Slopes with best-in-nation resources like the Lassonde Institute, participants have the opportunity to get their start-up off the ground.
Through a collective interest in algorithmic stock market trading, Takara Truong (mechanical engineering junior), Junyan He (mechanical engineering senior), and Austin Gibbons (computer science junior), developed a project that successfully unified their interest with Hackathon’s community theme.
In 24 hours, Takara’s team developed a framework that could incorporate several trading algorithm models into a single buy/sell/hold signal. Trading algorithms determine when a stock should be bought or sold depending on past information. The project was designed with modularity in mind. Individuals have the ability to design their own trading algorithms given a prescribed set of inputs and simply import the model into the framework. The framework then chooses the top performing algorithm using profit/loss ratio over a test window and uses that specific algorithm until a different algorithm has a higher profit/loss ratio.
The team created two algorithms for this framework: a moving average model and a machine learning model. As part of the demonstration, the framework was deployed onto the stock market where it bought and sold portions of real Bitcoin autonomously. Based on profit earned during the 2-hour demo time with initial investment of $1, the team calculated that they could raise one million dollars in approximately 58,000 years.
The team continues to improve the project in hopes of reducing the time needed to become millionaires. Of course all three members of the team winning their own PS4 is sure to help!
