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

Financial market applications of LLMs

thegradient.pub

Post reply on HN
Print view View original

41–50 of 116 posts

Re: Financial market applications of LLMs

#41

Post by hydershykh »

paulryanrogers wrote: post #40
hydershykh wrote: post #38

I think some of the financial applications around LLMs right now are better suited for things like summarization, aggregation, etc. We at Tradytics recently built two tools on top of LLMs and they've been super popular with our usercase. Earnings transcript summary: Users want a simple and easy to understand summary of what happened in an earnings call and report. LLMs are a nice fit for that - https://tradytics.com/…

As more of the reports get written by layers of AI it makes me wonder how lossy and noisy this whole pipeline is becoming.

That's a fair point. But models like GPT4 do not hallucinate much when it comes to summarizing. So I don't think these applications contribute to anything negative.

Re: Financial market applications of LLMs

#42

Post by actionfromafar »

nostrademons wrote: post #32
btbuildem wrote: post #30

There were some developments using LLMs in the timeseries domain which caught my attention. I toyed with the Chronos forecasting toolkit [1], and the results were predictably off by wild margins [2] What really caught my eye though was the "feel" of the predicted timeseries -- this is the first time I've seen synthetic timeseries that look like the real thing. Stock charts have a certain quality to them, once you've…

I used to work in financial software, and when writing the charting UIs, I'd wire them up to a randomwalk to generate fake time series data. It was a relatively common occurrence for a VP or the company CEO to walk by, look at my screen, and say "What stock is that? Looks interesting." Unpopular opinion backed up by experience: a randomwalk is the most effective model for generating timeseries that have the "feel" of…

Or it looked interesting because it did not look normal.

Re: Financial market applications of LLMs

#43

Post by actionfromafar »

kortilla wrote: post #35
ysofunny wrote: post #8

If I learned anything from a conference by benoit mandelbrot back in my college days is that gaming financial markets is the only real application of anything scientific but I vaguely remember what he was actually talking about, I never quite made it as a mathematician

What does that even mean? How is the atomic bomb not real?

The atomic bomb is used very much today to influence markets, to be fair.

Re: Financial market applications of LLMs

#44

Post by andoando »

AnthonyMouse wrote: post #31
carbotaniuman wrote: post #15

Earlier quoted context omitted.

I get that the perfectly efficient market is more of a model then something existing in reality, but who would be doing the arbitraging here?

Suppose the price of Amazon stock is going to be 20% higher tomorrow than it is today. If everyone knew this, the price would already be 20% higher, because the existing owners wouldn't sell at the lower price. If some people know this but not everyone, they'll keep buying Amazon stock until the price increases by 20%, which again causes the price to immediately increase by 20% instead of waiting until tomorrow. The…

Its crazy how many people don't understand this. I can't believe how many people think they could predict the market with candle light sticks or whatever. If a method for predicting the market is so readily available that someone is selling it to you, it eouldnt work!!

Re: Financial market applications of LLMs

#45

Post by fragmede »

__MatrixMan__ wrote: post #14
ben_w wrote: post #13

Earlier quoted context omitted.

"Buy index funds. The end." From what I've heard (and as finance isn't my field, my knowledge should be considered worse than ChatGPT ), if everyone had a truly omniscient genie, the markets would become perfectly efficient, and a perfectly efficient market has no room for profit because any profit opportunity is immediately arbitraged out of existence.

That should be the goal, right? Good ideas get the funding they need as if by magic, yet nobody is sitting on the sidelines collecting rent. The best thing that AI can do for finance is eliminate it.

that sounds really bad for everyone collecting rent

Re: Financial market applications of LLMs

#46

Post by iamgopal »

nostrademons wrote: post #32
btbuildem wrote: post #30

There were some developments using LLMs in the timeseries domain which caught my attention. I toyed with the Chronos forecasting toolkit [1], and the results were predictably off by wild margins [2] What really caught my eye though was the "feel" of the predicted timeseries -- this is the first time I've seen synthetic timeseries that look like the real thing. Stock charts have a certain quality to them, once you've…

I used to work in financial software, and when writing the charting UIs, I'd wire them up to a randomwalk to generate fake time series data. It was a relatively common occurrence for a VP or the company CEO to walk by, look at my screen, and say "What stock is that? Looks interesting." Unpopular opinion backed up by experience: a randomwalk is the most effective model for generating timeseries that have the "feel" of…

This is true, I have tested this with multiple veterans and none could tell them apart

Re: Financial market applications of LLMs

#47

Post by IAmGraydon »

nostrademons wrote: post #32
btbuildem wrote: post #30

There were some developments using LLMs in the timeseries domain which caught my attention. I toyed with the Chronos forecasting toolkit [1], and the results were predictably off by wild margins [2] What really caught my eye though was the "feel" of the predicted timeseries -- this is the first time I've seen synthetic timeseries that look like the real thing. Stock charts have a certain quality to them, once you've…

I used to work in financial software, and when writing the charting UIs, I'd wire them up to a randomwalk to generate fake time series data. It was a relatively common occurrence for a VP or the company CEO to walk by, look at my screen, and say "What stock is that? Looks interesting." Unpopular opinion backed up by experience: a randomwalk is the most effective model for generating timeseries that have the "feel" of…

That’s my experience as well. A random walk looks just like market data. You could even perform technical analysis on it, finding support, resistance, trendlines, etc. It really makes you realize why technical analysis doesn’t work.

Re: Financial market applications of LLMs

#48

Post by nostrademons »

actionfromafar wrote: post #42
nostrademons wrote: post #32

Earlier quoted context omitted.

I used to work in financial software, and when writing the charting UIs, I'd wire them up to a randomwalk to generate fake time series data. It was a relatively common occurrence for a VP or the company CEO to walk by, look at my screen, and say "What stock is that? Looks interesting." Unpopular opinion backed up by experience: a randomwalk is the most effective model for generating timeseries that have the "feel" of…

Or it looked interesting because it did not look normal.

It looked interesting because it was going up. The random-walks that trended sideways or downwards did not look interesting.

Re: Financial market applications of LLMs

#50

Post by multicast »

wuj wrote: post #39

HFTs exploit price inefficiencies that last only milliseconds. The time-series data mentioned in the article is on the scale of seconds. I wonder if its possible to get the time-series data on the scale of milliseconds, and how that would affect the training of the objective function in a LLM.

Todays derivatives and their pricing are based on the premise that stock prices can not be predicted and behave like a Brownian motion system. If you take real time data from any stock and calculate in order how many times a stock went up in a row or down in a row you end up almost perfectly with a natural probability distribution. HFT's are involved in market making and arbitrage both of which already involves high speed, the later much more, and earning minuscule profits. There are ghost patterns who can be mined for a certain period of time but they are not solely calculated based on trading time series. They involve complex proprietary calculations, some machine learning and relationships between stocks. There is no pattern in the flow how a particular stock is trading.

Also from a long-term view its very questionable. How should a model be able to predict that in the middle of a high interest environment, a tech bubble burst and a dumping stock market in general, a new platform called Chat-GPT gets launched that basically carries the whole world's stock market to new heights which causes among other things retail investors to liquidate bonds and other high interest environment assets and flood it into the stock market. It is more than completely of the text-book. That can not be predicted. The million dollar spending guy is at the end the same way off as the guy who simply employs a 100 python line trend-following strategy.

Post reply on HN