Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The anatomy of an ML-powered stock picking engine

principiamundi.com

Post reply on HN
Print view View original

11–20 of 109 posts

Re: The anatomy of an ML-powered stock picking engine

#11

Post by Straw »

muggermuch wrote: post #8
idoh wrote: post #6

If you have a tool that can generate great returns, then why fall back to a newsletter?

Great question. If I beat the market by 20% (say SPY generated 0% for the year, very optimistic at this point), and I have allocated $100k to this, I make $20k before taxes. That's less than minimum wage. Meanwhile, allocators expect a track record of at least 3-5 years. Ideally, if I have an asset, I'd like to extract as much revenue as I can. Hope this makes sense.

How difficult is it to get investors when you can show your model beats the market consistently?

Of course, they have to check your not trading a strategy with extreme tail risk, but here it sounds like that's not the case?

Re: The anatomy of an ML-powered stock picking engine

#12

Post by muggermuch »

Straw wrote: post #11
muggermuch wrote: post #8

Earlier quoted context omitted.

Great question. If I beat the market by 20% (say SPY generated 0% for the year, very optimistic at this point), and I have allocated $100k to this, I make $20k before taxes. That's less than minimum wage. Meanwhile, allocators expect a track record of at least 3-5 years. Ideally, if I have an asset, I'd like to extract as much revenue as I can. Hope this makes sense.

How difficult is it to get investors when you can show your model beats the market consistently? Of course, they have to check your not trading a strategy with extreme tail risk, but here it sounds like that's not the case?

It's difficult. We made a lot of pitches. Investors/allocators require a fairly long track record and are extremely reluctant to fund (what they perceive to be) black box strategies.

Re: The anatomy of an ML-powered stock picking engine

#15

Post by xapata »

muggermuch wrote: post #8
idoh wrote: post #6

If you have a tool that can generate great returns, then why fall back to a newsletter?

Great question. If I beat the market by 20% (say SPY generated 0% for the year, very optimistic at this point), and I have allocated $100k to this, I make $20k before taxes. That's less than minimum wage. Meanwhile, allocators expect a track record of at least 3-5 years. Ideally, if I have an asset, I'd like to extract as much revenue as I can. Hope this makes sense.

If you're sitting on a gold mine, you can wait 5 years. This does not make sense.

Re: The anatomy of an ML-powered stock picking engine

#18

Post by muggermuch »

ajoseps wrote: post #16

this is very cool! where did you get your data from and how's the transition to airflow?

There are commercial feeds available via Nasdaq DataLink (FKA Quandl). I also bought bulk historical data to feed through my backtester (I haven't talked about this in the post; it was getting to be a bit too long).

Re: The anatomy of an ML-powered stock picking engine

#19

Post by ramesh31 »

unpwn wrote: post #9

Lmao this engine is down 6.9% for the year, when literally it's as simple as just buying some puts.

> this engine is down 6.9% for the year

That’s pretty damn good, and still beating the market by nearly 20%. Of course you can always make more with riskier strategies.

Re: The anatomy of an ML-powered stock picking engine

#20

Post by muggermuch »

xapata wrote: post #15
muggermuch wrote: post #8

Earlier quoted context omitted.

Great question. If I beat the market by 20% (say SPY generated 0% for the year, very optimistic at this point), and I have allocated $100k to this, I make $20k before taxes. That's less than minimum wage. Meanwhile, allocators expect a track record of at least 3-5 years. Ideally, if I have an asset, I'd like to extract as much revenue as I can. Hope this makes sense.

If you're sitting on a gold mine, you can wait 5 years. This does not make sense.

Indeed. I haven't shut down development, just shut down the newsletter. I'm continuing to work on it.
Post reply on HN