News for hackers. Stuff that matters.
Re:The anatomy of an ML-powered stock picking engine by jesuslop on Tuesday September 27, 2022 @02:52PM (#32999477)
Nice report. How did you did risk management? Have you been leveraged? Have you paid for data? Kudos for a view from the trenches.
Re:The anatomy of an ML-powered stock picking engine by muggermuch on Tuesday September 27, 2022 @03:08PM (#32999725)
Thank you!

>How did you did risk management? I put in a basic position management layer (1% fixed stop). Also, the market regime module would modulate participation, i.e. in really risky environments it would dial down the number of stock picks. I can definitely do much more on this front, but I wanted to nail down the stock picking first! :)

>Have you been leveraged? No leverage.

>Have you paid for data? Yes, my monthly running costs for data are ~$1.2k.

Re:The anatomy of an ML-powered stock picking engine by pneumatic1 on Tuesday September 27, 2022 @05:24PM (#33001325)
Have you looked into Kelly criterion?
Re:The anatomy of an ML-powered stock picking engine by muggermuch on Tuesday September 27, 2022 @05:35PM (#33001416)
Yes! I use fractional Kelly extensively in my (separate) higher-frequency strategies (on MES/ES/NQ/VX futures).

I'm thinking of writing some follow-up posts on how to reason about ML-driven strategies in an intraday setting. Thanks to low-cost brokerages, there's a lot of alpha that can be captured by small league speculators such as myself.

Re:The anatomy of an ML-powered stock picking engine by Jorge1o1 on Tuesday September 27, 2022 @08:04PM (#33002770)
This is true. I ran a 3+ Sharpe and over 40% annualized strategy on PredictIt back when they had the tweet markets a few years ago. It was literally just fitting a Poisson model to Trump, Pence, White House, POTUS, and VP twitter accounts and then Kelly betting based on the difference between the market price and the Poisson model.

I strongly believe the only reason I got such a solid performance is not because I’m some kind of trading savant, but simply that the $850 per contract limit prevents smart money/institutional traders from moving the market towards efficiency.

Similar opportunities exist in the equity world — one huge advantage is that little guys don’t really incur market impact.

For a lot of systematic RV plays, you might only have 10bps alpha and then a 7bp trading cost each way.

Re:The anatomy of an ML-powered stock picking engine by JSGdev on Wednesday September 28, 2022 @10:24AM (#33008313)
what data sources did you use? im interested in working on something similar.