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

Financial Statement Analysis with Large Language Models

papers.ssrn.com

Post reply on HN
Print view View original

181–190 of 219 posts

Re: Financial Statement Analysis with Large Language Models

#181

Post by mistermann »

staunton wrote: post #133
flourpower471 wrote: post #107

Earlier quoted context omitted.

It is just a different (applied) discipline. It's like math v engineering - you can come up with some beautiful pde theory to describe this column in a building will bend under dynamic load and use it to figure out exactly the proportions. But engineering is about figuring out "just make its ratio of width to height greater than x" Because the goal is different - it's not about coming up with the most pleasing descri…

> The three body problem is also harder than running experiments in the LHC or analysing Hubble data or treating sick kids or building roads or running a business Not that it's particularly relevant to this discussion but the three body problem is easy. You can solve it numerically on a laptop with insane precision (much more precisely than would be useful for anything) or also write down an analytic solution (which…

From your link:

> Unlike the two-body problem, the three-body problem has no general closed-form solution,[1] and it is impossible to write a standard equation that gives the exact movements of three bodies orbiting each other in space.

This seems like the opposite of your claim.

Re: Financial Statement Analysis with Large Language Models

#182

Post by Krasnol »

SavageBeast wrote: post #36
bossyTeacher wrote: post #33

Earlier quoted context omitted.

>People didn't stop working on this in 1989 - they realised they can make lots of money doing it and do it privately. Mind elaborating?

Speaking for myself and likely others with similar motivations, yes we can "figure it out" and publish something to show our work and expand the field of endeavor with our findings - OR - we can figure something profitable out on our own and use our own funds to trade our strategies with our own accounts. Anyone who has figured out something relatively profitable isn't telling anyone how they did it.

Wouldn't publishing also influence the performance itself because it would also make an impact on the data? And if you'd calculate that in and the method is spreading, wouldn't that in turn have to be calculated in also, which would lead to a spiral?

Re: Financial Statement Analysis with Large Language Models

#184

Post by perkolator »

doctoboggan wrote: post #38

If this were to become widely used, I can imagine executives writing financial statements, running them through an LLM, and tweaking it until they get the highest predicted future outcome. This would make the measure almost immediately useless.

Anyone who has read many financial statements would understand this whole idea is already useless outside of financial statement education.

LLMs could help a person learn to understand financial statements better, that is it.

There are not all these hidden gems in financial statements though that are being currently missed that language models are going to unearth.

Financial statements are already intentionally vague and often intentionally misleading.

Corporate CEO/PR/Marketing are already the masters of writing many words while saying absolutely nothing.

Re: Financial Statement Analysis with Large Language Models

#185

Post by DeathArrow »

posting_mess wrote: post #60
bethekind wrote: post #24

Earlier quoted context omitted.

Do you use llama 3 for your work?

No hedge fund registered before the last 2 weeks will use Llama3 for their "prod work" beyond "experiments". Quant trading is about "going fast" or "being super right", so either you'd need to be sitting on some huge llama.cpp/transformer improvement (possible but unlikely) or its more likely just some boring math applied faster than others. Even if they are using a "LLM", they wont tell you or even hint at it - "eff…

>Quant trading is about "going fast" or "being super right",

Going fast means scalping?

Re: Financial Statement Analysis with Large Language Models

#186

Post by threeseed »

kortilla wrote: post #176
flourpower471 wrote: post #107

Earlier quoted context omitted.

It is just a different (applied) discipline. It's like math v engineering - you can come up with some beautiful pde theory to describe this column in a building will bend under dynamic load and use it to figure out exactly the proportions. But engineering is about figuring out "just make its ratio of width to height greater than x" Because the goal is different - it's not about coming up with the most pleasing descri…

You misunderstand the quote. It’s where brains go to die from a societal perspective. It might be stimulating and difficult for the individual but it’s useless to science.

Many advancements in computer science have come from the finance world.

e.g. LMAX Disruptor was a pretty impressive concurrency library a decade ago:

https://lmax-exchange.github.io/disruptor/

Re: Financial Statement Analysis with Large Language Models

#187

Post by staunton »

mistermann wrote: post #181
staunton wrote: post #133

Earlier quoted context omitted.

> The three body problem is also harder than running experiments in the LHC or analysing Hubble data or treating sick kids or building roads or running a business Not that it's particularly relevant to this discussion but the three body problem is easy. You can solve it numerically on a laptop with insane precision (much more precisely than would be useful for anything) or also write down an analytic solution (which…

From your link: > Unlike the two-body problem, the three-body problem has no general closed-form solution,[1] and it is impossible to write a standard equation that gives the exact movements of three bodies orbiting each other in space. This seems like the opposite of your claim.

The crucial parts of that are "closed-form" and "standard". The analytic solution is "non-standard" because it involves the kind of power series that nobody knows or cares about (because they are only about 100 years old and have no real useful applications in engineering).

A similar claim is that roots of polynomials of degree 5 (and over) have no "general closed form solution" (with, as usual, the implicit qualification: "in terms of functions I'm currently comfortable with because I've seen them a lot"). That doesn't mean it's a difficult problem.

The two problems have in common that they are significantly harder than their smaller versions (two bodies, or degree 4). Historically, people spent a lot of time trying to find solutions for the larger problems in terms of the same functions that can be used to solve the smaller problems (conic sections, radicals). That turned out to not be possible. This is the historical origin of the meme "three body problem is unsolvable".

Re: Financial Statement Analysis with Large Language Models

#188

Post by onion2k »

BobaFloutist wrote: post #50
andsoitis wrote: post #44

Earlier quoted context omitted.

> Anyone who has figured out something relatively profitable isn't telling anyone how they did it. Corollary: someone who is selling you tools or strategies on how to make tons and tons of money, is probably not making tons and tons of money employing said tools and strategies, but instead making their money by having you buy their advice.

I think I could probably make more money selling a tool or strategy that consistently, reliably makes ~2% more than government bonds than I could make off it myself, with my current capital.

If you can prove it works you won't have any difficulty raising capital.

Re: Financial Statement Analysis with Large Language Models

#190

Post by rafaelero »

perkolator wrote: post #184
doctoboggan wrote: post #38

If this were to become widely used, I can imagine executives writing financial statements, running them through an LLM, and tweaking it until they get the highest predicted future outcome. This would make the measure almost immediately useless.

Anyone who has read many financial statements would understand this whole idea is already useless outside of financial statement education. LLMs could help a person learn to understand financial statements better, that is it. There are not all these hidden gems in financial statements though that are being currently missed that language models are going to unearth. Financial statements are already intentionally vague…

Still, if you use GPT-4 it gives you 60% of accuracy in predicting if it's going to go up and down, which is considerably better than median human forecasters. Stop being so dismissive and start reading the numbers.
Post reply on HN