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. The next week you have ChatGPT produce 50000 predictions and send them out to those winners, you now have 25000 who have gotten two good predictions.
Rinse and repeat four more times and congratulations, you now have a client list of over 1500 people who have received six weeks of good predictions and are ready for you to manage all of their wealth using these insanely accurate AI predictions.
[1] https://www.washingtonpost.com/archive/business/2004/06/20/a...
Its amazing to see the people that won on the previous Nth rounds believe that their next tip was a "sure thing".
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 "${ticker} will go up more than the market tomorrow, I'd recommend you invest and hedge with a bet against the market" for a variety of random tickers, I'd guess around half of them would pay off.
It's too bad that prediction is functionally overrated in trading anyway, and the overrating is even worse when it's being done by beginners.
Everybody wants an edge on the future, but few can hold a really solid trading plan together over a significant amount of time. Especially when they've already even blown up an account, etc.
You can make a pretty good argument that things like emotional dynamics and emotional leverage at a personal level are at least as important as prediction, but maybe more if you consider that you can find a reasonable predictive model built on something as valid as mean regression after a minute's searching around.
The experiences shared in the _Wizards_ books are pretty remarkable in this way.
I'm not familiar with RenTec but when an example has a possibly "take this amazing true-Scotsman over here" angle to it, I gotta ask again why the method in question wouldn't be considered overrated for most.
Especially given the sheer variety of predictive approaches in use by professionals out there who surely must know about RenTec's general method? Is it a specification that's different? Do others expect even higher returns over a shorter timeline? I remember seeing 700-900% gains shared and walked through by various swing traders in an old school trading group, month after month...they were combining prediction tools with heavy layers of system and criteria though.
I also don't see where the long-short criteria is defined for Figure 1: Cumulative Returns of Investing 1$ (Without Transaction Costs). How do you know when to flip between long and short? Moving average crossover?
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
people keep bringing this up. What evidence is there that this is his firm's method? And if so, how would it work.
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.
1. Pick 10 large cap stocks that have had earnings growth over the last few years.
2. Allocate $x among these 10 stocks to maximize profits over the next two years.
It did #1.
It refused to do #2.
Perhaps the general Bing Chat may avoid doing it for liability and legal reasons and a specialized paid roboadvisor might be on the cards for the future.
Of course the data it gives you then is completely made up, but that's not the point :P
[1] - https://en.wikipedia.org/wiki/Jim_Simons_(mathematician)
I'd personally rather see it predict the weather in some ways, for one because the insights would be more instantly tractable.
So I think the actual question here is: What happens when you can make these predictions without hiring dozens of Ph.Ds and paying them oodles of money?
[1] Prompt: Are you familiar with Warren Buffet's Letters to Shareholders?
Yes, I'm familiar with Warren Buffett's Letters to Shareholders. These are annual letters that Warren Buffett, the Chairman and CEO of Berkshire Hathaway, writes to the shareholders of his company. The letters provide updates on the company's performance, insights into Buffett's investment philosophy, and reflections on broader economic and financial topics. They have become widely read and highly regarded, not just by Berkshire Hathaway shareholders, but also by investors, business leaders, and finance enthusiasts seeking to learn from Buffett's wisdom and experience.
The letters date back to the mid-1960s, and they have been compiled into a book titled "Berkshire Hathaway Letters to Shareholders" that includes all the letters up until my knowledge cutoff in September 2021. Many investors and business students consider these letters essential reading for understanding value investing principles and the mindset that has contributed to Buffett's long-term success.
Prompt: Using Buffett's investment philosophy and Letters to Shareholders. Will you help me analyze some stocks?
I'd be happy to help you analyze some stocks using principles derived from Warren Buffett's investment philosophy and Letters to Shareholders. Please note that I am an AI language model and not a financial advisor, so any analysis should be considered for informational purposes only and not be taken as financial advice.
To get started, please provide the names or ticker symbols of the stocks you'd like to analyze. Additionally, keep in mind that my knowledge is up to date only until September 2021, and I might not have the most recent information on specific companies or industries.
Prompt: Lets start with RIVN
Rivian Automotive, Inc. (RIVN) is an American electric vehicle (EV) manufacturer founded in 2009. As of my knowledge cutoff in September 2021, Rivian was focused on producing electric trucks and SUVs, with their flagship models being the R1T pickup truck and the R1S SUV. Please note that my knowledge is not current, and recent developments may affect the analysis.
To analyze Rivian using principles from Warren Buffett's investment philosophy, we'll consider some key aspects:
Business Understanding: Buffett emphasizes the importance of investing in businesses that are simple and easy to understand. Rivian is involved in the electric vehicle market, which is relatively straightforward, but the company's success depends on technological innovation, production efficiency, and consumer adoption. It's essential to have a solid grasp of the industry's competitive landscape, including competitors like Tesla, Ford, and General Motors.
Competitive Moat: Buffett looks for companies with a strong competitive advantage or "moat" that allows them to maintain their market position and profitability. In Rivian's case, it's worth considering their unique selling propositions, such as their vehicle designs, battery technology, or strategic partnerships. Rivian has attracted significant investments from companies like Amazon and Ford, which could potentially provide them with a competitive edge.
Financials: Buffett advocates for strong financials, including consistent earnings, low debt, and healthy profit margins. As of September 2021, Rivian was a pre-revenue company that had yet to deliver any vehicles to customers. Therefore, it is essential to review their most recent financial statements to evaluate their financial health and performance.
Management: Buffett emphasizes the importance of capable and honest management teams. Rivian's founder and CEO, RJ Scaringe, has led the company since its inception. Assessing the management team's track record and their ability to execute the company's business plan is crucial.
Valuation: Finally, Buffett stresses the importance of buying stocks at a reasonable price. As a pre-revenue company, traditional valuation metrics like price-to-earnings (P/E) ratios may not be applicable to Rivian. Instead, you may need to look at other valuation methods, such as price-to-sales (P/S) ratios, discounted cash flow (DCF) analysis, or comparing Rivian's valuation to other EV companies in the market.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 uses ChatGPT for sentiment analysis, but I think an even bigger leap is going to be getting actual meaning out of news and financial reports more efficiently.
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."
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.
