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

ChatGPT can help yield more accurate stock trading predictions – study

papers.ssrn.com

Post reply on HN
Print view View original

31–40 of 58 posts

Re: ChatGPT can help yield more accurate stock trading predictions – study

#31

Post by ckardat123 »

paulpauper wrote: post #26
gooseus wrote: post #19

I feel compelled to write this though it's only tangentially relevant to the article and is an adaptation of Taleb's story of stock-picking monkeys[1] from either Fooled by Randomness or The Black Swan: Say you have an email list of 100000 investors, you ask ChatGPT to produce 100000 predictions and send these out to each investor. Assuming ChatGPT is as good as a coin flip, 50000 investors receive good predictions.…

What sort of market prediction is decided by coin flip though? This makes more sense in the context of a binary outcome like sports betting in which you are betting on a team either winning or losing.

The scheme definitely could get foiled if people were just told that a certain stock would go up (without hedging against the market), because if it's a red day for the market the whole e-mail list could get wiped out as all the stocks go down.

I would think that there is approximately a 50% chance of most stocks beating the market on any given day though.

If you send a bunch of e-mails saying "${ticker} will go up more than the market tomorrow, I'd recommend you invest and hedge with a bet against the market" for a variety of random tickers, I'd guess around half of them would pay off.

Re: ChatGPT can help yield more accurate stock trading predictions – study

#32

Post by skizm »

jrpt wrote: post #18

I've found it useful using LLMs to help understand company 10-K reports like these: https://docalysis.com/library/10-k-reports For example, I used it to understand how much Meta is investing in its Reality Labs initiatives ($13.7 billion last year) as well as how much revenue Reality Labs brought in ($2.15 billion). I'm certain financial professionals are using it to better understand the world. The paper says it use…

Except that is completely wrong. Reality Labs revenue was $2.16B and Reality Labs total loses were $13.7B for 2022 (table on page 119).

Also this quote: "For example, our investments in Reality Labs reduced our 2022 overall operating profit by approximately $13.72 billion, and we expect our investments to increase in the future."

Re: ChatGPT can help yield more accurate stock trading predictions – study

#33

Post by alkonaut »

paulpauper wrote: post #26
gooseus wrote: post #19

I feel compelled to write this though it's only tangentially relevant to the article and is an adaptation of Taleb's story of stock-picking monkeys[1] from either Fooled by Randomness or The Black Swan: Say you have an email list of 100000 investors, you ask ChatGPT to produce 100000 predictions and send these out to each investor. Assuming ChatGPT is as good as a coin flip, 50000 investors receive good predictions.…

What sort of market prediction is decided by coin flip though? This makes more sense in the context of a binary outcome like sports betting in which you are betting on a team either winning or losing.

It doesn't matter that it's not a binary choice to pick a stock, you can convert it into a binary choice at will. For example, you can send out 1M emails with stock recommendation for some large stock with "buy" or "sell" as a 50/50 coin flip. You didn't pick the stock, you chose between buy/sell, the outcome will be the same: your market prediction skill will look fantastic to a select few.

Re: ChatGPT can help yield more accurate stock trading predictions – study

#34

Post by broast »

paulpauper wrote: post #30
broast wrote: post #14

It's almost certainly expected. These models are argued to contain hidden models of the data they represent, and can pick up on patterns with one-shot or few-shot samples Let's recall that Bob Mercer, Jim Simons made their billions off of trading options with NLP based hidden markov models, beating everyone on Wall St for the last two decades. ChatGPT is an easy entry to this

hidden markov models people keep bringing this up. What evidence is there that this is his firm's method? And if so, how would it work.

Just Jim Simon's own words, in the book The Man Who Solved The Market. And the fact that they hired NLP engineers explicitly.

My guess is it would be momentum based and capturing short term fluctuations in the market. My guess is they would train a markov decision policy on sequences of moves, and try to predict the next one, and trade on it with some sophisticated risk management.

Re: ChatGPT can help yield more accurate stock trading predictions – study

#35

Post by KeplerBoy »

ckardat123 wrote: post #31
paulpauper wrote: post #26

Earlier quoted context omitted.

What sort of market prediction is decided by coin flip though? This makes more sense in the context of a binary outcome like sports betting in which you are betting on a team either winning or losing.

The scheme definitely could get foiled if people were just told that a certain stock would go up (without hedging against the market), because if it's a red day for the market the whole e-mail list could get wiped out as all the stocks go down. I would think that there is approximately a 50% chance of most stocks beating the market on any given day though. If you send a bunch of e-mails saying "${ticker} will go up m…

Beating the market also means just falling less than the index on some days. Not sure if those customers would be happy.

The reverse also applies a.k.a. everyone could make money in the past few years.

Re: ChatGPT can help yield more accurate stock trading predictions – study

#36

Post by fabiospampinato »

jwhiles wrote: post #29
paulpauper wrote: post #26

Earlier quoted context omitted.

What sort of market prediction is decided by coin flip though? This makes more sense in the context of a binary outcome like sports betting in which you are betting on a team either winning or losing.

Buy stock X - it will definitely go up in the next week!

Though it's not like 50% of the days any given stock goes up and the other 50% of the days the stock goes down.

Re: ChatGPT can help yield more accurate stock trading predictions – study

#37

Post by zevv »

If any AI - or any other process or algorithm - would be able to provide significant better predictions than what is currently used, wouldn't this affect the stock prices as soon as this gets deployed by brokers at scale, effectively making the predictions useless again?

Re: ChatGPT can help yield more accurate stock trading predictions – study

#38

Post by datadata »

paulpauper wrote: post #26
gooseus wrote: post #19

I feel compelled to write this though it's only tangentially relevant to the article and is an adaptation of Taleb's story of stock-picking monkeys[1] from either Fooled by Randomness or The Black Swan: Say you have an email list of 100000 investors, you ask ChatGPT to produce 100000 predictions and send these out to each investor. Assuming ChatGPT is as good as a coin flip, 50000 investors receive good predictions.…

What sort of market prediction is decided by coin flip though? This makes more sense in the context of a binary outcome like sports betting in which you are betting on a team either winning or losing.

You could get close to a binary output with an option spread with a tight range of strikes (e.g. buying a call at price X, and selling a call at price X+1). If the stock price goes above the high strike it is a maximal payout one way, and below the low strike maximal payout the other way. If the strikes are close compared to movements of the stock and near the current price of the stock, the outcome is likely to be nearly binary. If the stock settles between the strikes the payout would be partial and continuous, but that window is very small.

Re: ChatGPT can help yield more accurate stock trading predictions – study

#39

Post by jrpt »

skizm wrote: post #32
jrpt wrote: post #18

I've found it useful using LLMs to help understand company 10-K reports like these: https://docalysis.com/library/10-k-reports For example, I used it to understand how much Meta is investing in its Reality Labs initiatives ($13.7 billion last year) as well as how much revenue Reality Labs brought in ($2.15 billion). I'm certain financial professionals are using it to better understand the world. The paper says it use…

Except that is completely wrong. Reality Labs revenue was $2.16B and Reality Labs total loses were $13.7B for 2022 (table on page 119). Also this quote: "For example, our investments in Reality Labs reduced our 2022 overall operating profit by approximately $13.72 billion, and we expect our investments to increase in the future."

Sorry, I put the wrong number in my comment. You can see the LLMs can understand it properly. Here's a screenshot where I just double checked: https://i.imgur.com/Xu1X2zC.png

Re: ChatGPT can help yield more accurate stock trading predictions – study

#40

Post by kljlkjfdsjlk »

jrpt wrote: post #18

I've found it useful using LLMs to help understand company 10-K reports like these: https://docalysis.com/library/10-k-reports For example, I used it to understand how much Meta is investing in its Reality Labs initiatives ($13.7 billion last year) as well as how much revenue Reality Labs brought in ($2.15 billion). I'm certain financial professionals are using it to better understand the world. The paper says it use…

I tried your website thought of a question to ask and then your bot said something about scammers and needing to sign up.

Some meddling advice 1) think about giving an easy-win to users so they actually want to sign up. You didn't give one, and in fact surprise users in an annoying way because you don't tell users they need to sign up until after they've already submitited their question. Not even a teaser, just completely zero value.

2) be upfront when you're affiliate with a product. HN isn't totally against about self-promotion, but you have to be upfront about it being your product and not just a cool thing you're using.

Post reply on HN