In the thrilling contest of high-frequency trading, my squad is called ‘MONOPOLY’ inspired by Ariana Grande’s hit single of the same name. The song is about “friendship, freedom, protecting your energy and staying right in your bag. We’re all about that life in the lab — working hard and spilling the tea on all things academic.
I spent the whole day diving into developing a DRL algorithm for our HFT contest — it’s both a blast and a bit of a time sink, considering opportunity cost. But anyway, I got our code up and running and even churned out some early results.
This contest keeps things simple: create an algorithm that knows when to hit ‘sell’ or ‘buy’ for each stock at the right minute. It’s so straightforward, someone might just win by throwing darts at a board—randomly, but hey, that’s not my style. I tried wrapping my head around some dense HFT literature, but it felt like reading a foreign language, so eventually I just go with DRL.
After some serious time debugging and code-slinging, thankfully, GPT-4.0 was like a coding sidekick, making sure it wasn’t too heavy a lift. And I’m thinking, once this contest is over, I might just dish out all the dirty details in a blog series — the good, the bad, and the ugly of how it all went down.
For now, though, I need to get another training model up on the server before dreamland calls. Night~