Software Engineer Looking for Investments / Sharing My Work
January 02, 2026
by a searcher from University of Chicago in St. Augustine, FL, USA
Hey folks, Happy New Year!
I'm an algorithms engineer in high frequency trading. Love working with large data!
Have seen a number of great posts here on the value of proprietary sourcing. I'm working on my own search, and for better or worse I have a mindset that is "automation, automation, automation".
I've found some of the best (and free!) data for US domiciled businesses is in the state managed corporate filing directories. So far I've encountered relatively shabby schema enforcement / scalable accessibility on the web. Florida for example offers an sftp site to do direct download. Once I got the data cleaned, joined against other sources it's been a great resource.
I'm working on some models for high-dimensionality vector embedding of SMBs, just to explore the feasibility of generating a target universe from plain text. I'm also tinkering with some due diligence automations hooking into NetSuite / QuickBooks.
If there are folks in the community that are thinking "I wish I had a more scalable way to access state managed databases directly", let me know in the comments what state(s) are most interesting to you and I'll build it out.
Also interested in hearing ideas for automations in general!
Cheers,
P.S. If you have any interesting data-engineering / automations problems related to a business you are evaluating or operating, feel free to shoot me an email below.
redacted