using chatgpt to predict stock prices

[vanzandt]

Why do you think hft pay vasts amounts of money for alternative data. .

I like to fly my toy drone over the TSLA factory and count the new cars out in the lot waiting to get shipped out 3X/day. I pay some nuns that run an orphanage in China to do it over there for me too.

 

[M.W.]

There is a Frenchman who inspects cocoa plants across Ghana and makes a killing selling that information to hedge funds in the US. The story crossed my table a while ago but I remember he expanded his products of choice greatly since.

Quality alternative data are incredibly valuable. If you don't see that but are interested I can send you some links to research. I work in this space.

I like to fly my toy drone over the TSLA factory and count the new cars out in the lot waiting to get shipped out 3X/day. I pay some nuns that run an orphanage in China to do it over there for me too.

 

[SunTrader]

Predicting has to deal with the "observer effect" as well.

 

[newwurldmn]

Largely on macro fund flows.
then on revaluation of news (like positive earnings)
Then on fear and greed (irrational)

with computers 1 has largely been arbed out. 2 has diminished a lot. (Back in Ben Graham’s day, a mis pricing could last for months; now it lasts for minutes).
3. might be exacerbated

That comes down to what you think drives the stock market. There are many factors, not all are observable. That's why no one really knows where AAPL stock will be at the close tomorrow. Will it be up or down? No one really knows. Take the most informed market participants on Wall Street, ask them where the market will close tomorrow, up or down? Their average prediction accuracy will be a little higher than 50% if they just say "higher" every day (market goes up more often than down). Few can predict much better than that over a long period of time. I don't see how an AI can improve on that, at least with long-term predictions. Short-term trading, maybe. Btw, there's already AI robo-funds, most I have seen such as this:

https://www.qraftaietf.com/

Underperform the market.

 

[guest_trader_1]

I've just asked it this question:

So, nah, this thing can't make you rich yet.

 

[SunTrader]

I've just asked it this question:

So, nah, this thing can't make you rich yet.

View attachment 302637

That works ... if one believe the random walk nonsense Academia ( aka those who can't) came up with.

 

[guest_trader_1]

That works ... if one believe the random walk nonsense Academia ( aka those who can't) came up with.

I am sure that you and your amazing technical analysis skills can predict a random walk, you should write a book. I'll be your biggest fan.

 

[SunTrader]

I am sure that you and your amazing technical analysis skills can predict a random walk, you should write a book. I'll be your biggest fan.

I can't ... predict something that doesn't exist.

Well I suppose I could, but what's the sense in that?

 

[ET180]

Why do you think hft pay vasts amounts of money for alternative data. It's to push up that edge by some positive delta.

You are mixing up entirely different domains. Long term investors suffer significant risks that hft algorithms don't and vice versa. Different types of risk. The normalized metric to compare is "edge" not total return or win probabilities on individual trades.

The long-term is simply more uncertain than the short-term. That idea is apparent in option pricing. Because many of the factors that drive long-term price movement are not observable, I don't think AI will ever be able to overcome that. Short-term, there are fewer factors that significantly move price. Perhaps, those factors tend to be more observable and quantifiable as well such that AI could provide an advantage...possible, but not my area of expertise.

 

[schizo]

This is a pretty cool video