Financial Statement Analysis with Large Language Models • Hacker News Board

Re: Financial Statement Analysis with Large Language Models

#191

Post by SCM-Enthusiast » Sat, May 25, 2024, 1:11 PM UTC

famouswaffles wrote: post #142

caseyy wrote: post #87

> In this section, we aim to understand the sources of GPT’s predictive ability. Oh boy... I wonder how a neural net trained with unsupervised learning has a predictive ability. I wonder where that comes from... Unfortunately, the article doesn't seem to reach a conclusion. > We implement the CoT prompt as follows. We instruct the model to take on the role of a financial analyst whose task is to perform financial sta…

>Who will tell them how an LLM works and that the neural net does not calculate anything? You don't understand LLMs as well as you think you do. Yes, the neural network calculates things. >It only predicts the next token in a sentence of a calculation if it's been loss-minimized for that specific calculation. No that's not necessary at all. https://www.alignmentforum.org/posts/N6WM6hs7RQMKDhYjB/a-mec... https://cprim…

Phase changes and grokking make me nervious... It seems once you reach a certain threshold of training, you can continually "phase-change" and generate these emergent capabilities. This does not bode well for alignment.

Re: Financial Statement Analysis with Large Language Models

#192

Post by tempusalaria » Sat, May 25, 2024, 1:38 PM UTC

surfingdino wrote: post #28

nicce wrote: post #22

What will happen if everyone starts using heavy statistical methods or LLMs to predict stocks prices? And buys stock based on them? Will it absolutely make everything unpredictable? Edit: assuming that they initially provide good predictions

HFT guys won't touch GPT. The stakes are too high. If LLMs could give those guys an edge they'd be all over this tech.

A number of quant firms are among the largest global consumers of commercial LLMs

The only area you absolutely can’t use LLMs is in sub ms latency

Re: Financial Statement Analysis with Large Language Models

#193

Post by lordnacho » Sat, May 25, 2024, 2:06 PM UTC

makestuff wrote: post #138

flourpower471 wrote: post #103

Earlier quoted context omitted.

Well I work in prop trading and have only ever worked for prop firms- our firm trades it's own capital and distributes it to the owners and us under profit share agreements - so we have no incentive to sell ourselves as any smarter than the reality. Saying it's all high school math is a bit of a loaded phrase. "High school math" incorporates basically all practical computer science and machine learning and statistics…

Would you ever go off on your own to trade solo or is that something that just does not work without a ton (like 9 figures) of capital and a pretty large team?

It's like any other business, there are factors of production that various actors will have varying access to, at varying costs.

A car designer still needs a car factory of some sort, and there's a negotiation there about how the winnings are divided.

In the trading world there are a variety of strategies. Something very infra dependent is not going to be easy to move to a new shop. But there are shops that will do a deal with you depending on what knowledge you are bringing, what infra they have, what your funding needs are, what data you need, and so on.

Re: Financial Statement Analysis with Large Language Models

#194

Post by passwordle » Sat, May 25, 2024, 2:18 PM UTC

makestuff wrote: post #138

flourpower471 wrote: post #103

Earlier quoted context omitted.

Well I work in prop trading and have only ever worked for prop firms- our firm trades it's own capital and distributes it to the owners and us under profit share agreements - so we have no incentive to sell ourselves as any smarter than the reality. Saying it's all high school math is a bit of a loaded phrase. "High school math" incorporates basically all practical computer science and machine learning and statistics…

Would you ever go off on your own to trade solo or is that something that just does not work without a ton (like 9 figures) of capital and a pretty large team?

Going solo in trading is a very different beast compared to trading at a prop firm. Yes, capital is a significant factor. The more you have, the more you can diversify and absorb losses which are inevitable in trading. However, it's not just about the capital. The infrastructure, data access, and risk management systems at a prop firm are usually far superior to what you could afford or build on your own as an individual trader.

Moreover, the collaborative environment at a prop firm can't be understated. Ideas and strategies are continuously debated, tested, and refined. This collective brainpower often leads to more robust strategies than what you might come up with on your own.

That said, there are successful solo traders, but they often specialize in niche markets where they can leverage unique insights or strategies that aren't as capital intensive. It's definitely not for everyone and comes with its own set of challenges and risks.

Re: Financial Statement Analysis with Large Language Models

#195

Post by Panzer04 » Sat, May 25, 2024, 2:18 PM UTC

staunton wrote: post #187

mistermann wrote: post #181

Earlier quoted context omitted.

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 qualific…

Ill probably go look this up, but do you mean functions of a higher type than normal powers like eg. Tetration, or something more complicated (am I even on the right track?)

Re: Financial Statement Analysis with Large Language Models

#196

Post by nextworddev » Sat, May 25, 2024, 2:35 PM UTC

hadlock wrote: post #171

nextworddev wrote: post #71

To everyone thinking they can sell a LLM wrapper based on this - this is a very tough domain. You will soon run into data, distribution, and low demand. Funds that would actually use this are already using it.

Most every company I know has had a drag and drop PDF to LLM tool since Q1 2023. It's not a phenomenally difficult product to code up.

Not talking about a Chat-with-PDF solution. Talking about some large scale SEC filing analysis and visualization solution.

Re: Financial Statement Analysis with Large Language Models

#197

Post by anonu » Sat, May 25, 2024, 2:50 PM UTC

From a first principles approach: it does not really make sense to use an LLM to do fundamental analysis directly. Maybe you can use an LLM to write some python code to do fundamental analysis. But skipping that model building step and just applying a language model to numbers does not make intuitive sense to me.

I am surprised at the results in the paper. The biggest red flag is that the researcher are not sure why there is predictive ability in LLMs. Maybe they didn't control for some lookahead bias.

Re: Financial Statement Analysis with Large Language Models

#198

Post by anonu » Sat, May 25, 2024, 3:44 PM UTC

primitivesuave wrote: post #13

The area where I see this making the most transformational change is by enabling average citizens to ask meaningful questions about the finances of their local government. In Cook County, Illinois, there are hundreds of local municipalities and elected authorities, all of which are producing monthly financial statements. There is not enough citizen oversight and rarely any media attention except in the most egregious…

The most transformational change is by enabling average citizens to ask meaningful questions about their finances.

Around half of adults in the US are financially illiterate.

Re: Financial Statement Analysis with Large Language Models

#199

Post by staunton » Sat, May 25, 2024, 3:58 PM UTC

Panzer04 wrote: post #195

staunton wrote: post #187

Earlier quoted context omitted.

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 qualific…

Ill probably go look this up, but do you mean functions of a higher type than normal powers like eg. Tetration, or something more complicated (am I even on the right track?)

I mean functions defined by power series (just like sin(x) is defined in analysis courses). For the three body problem, see http://oro.open.ac.uk/22440/2/Sundman_final.pdf (Warning, pdf!). This is what Wikipedia cites when talking about the solution to the three body problem. The document gives a lout of historical context.

For polynomial roots, see wikipedia.org/wiki/Elliptic_function.

Re: Financial Statement Analysis with Large Language Models

#200

Post by JumpCrisscross » Sat, May 25, 2024, 7:00 PM UTC

FabHK wrote: post #158

JumpCrisscross wrote: post #119

Earlier quoted context omitted.

> the way to calculate the price of an Option/Derivative hasn't changed in my understanding for 20/30 years Not true. Most of the magic happens in estimating the volatility surface, BSM's magic variable. But I've also seen interesting work in expanding the rates components. All this before we get into the drift functions.

While the industry has changed substantially since the GFC, all foundational derivatives models were basically in place back then.

> all foundational derivatives models were basically in place back then

In vanilla equity options, sure. But that’s like saying we solved rockets in WWII. The foundational models were derived by then; everything that followed was refinement, extension and application.