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

Show HN: TrendFi – I built AI trading signals that self-optimize

trend.fi

Post reply on HN
Print view View original

31–40 of 56 posts

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#31

Post by runako »

selectodude wrote: post #28
runako wrote: post #18

Earlier quoted context omitted.

200%/yr starting from $10,000 => still needs a day job for a number of years. This is why Wall Street is able to hire talented young traders, some of whom will develop profitable systems. Over time, some of them are able to amass enough savings and the track record necessary to get investors. But at t=0, somebody has to pay the rent.

If you returned 200%/yr, you'd be running a fund an multiple times more successful than Renaissance's Medallion fund and would be able to attract outside capital and become a billionaire many times over in maybe five years.

Obviously 200% is not realistic. But, entertaining the claim, even if you can do 200% annually, you still have to earn money in the near term unless you have a pot of cash so you can both invest and live.

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#32

Post by ImPostingOnHN »

wolfman1 wrote: post #30
ImPostingOnHN wrote: post #17

Earlier quoted context omitted.

- From where, then, did you get the info that "they consistently outperform buy and hold for 10+ years now" ? - What does "they're the real deal" mean? - Two years is not enough to test a strategy like this. 20 years would be better better, but it sounds like they already did that and the strategy fails half the time (hence the 10-year claim)? Does it fail randomly, or did they market a strategy that worked for the f…

They're the real deal means they're not a scam. I don't know everything about their business. I recommend just looking at their website. They've been in business for nearly 20y and have consistently outperformed buy & hold.

> they're not a scam.

Nobody explicitly said it was a scam, just that the claims are questionable and unverified. There's certainly no shortage of people on the internet who claim to have a get-rich-quicker-than-average scheme with claims exactly along these lines. Obviously those claims should be verified.

> I recommend just looking at their website.

A random website can't be trusted as an unbiased source about itself. I did check their website, but couldn't find anything there regarding your claims that was independently verified.

> [Chris has] consistently outperformed buy & hold [for 10+ years].

This is literally one of the most common hook/marketing lines from investment advice "businesses"/scammers.

---> Where did you learn this? ---> How do you know it is true? ^--- These questions should be answered if one wishes to avoid scams, just as a general life rule.

> They've been in business for nearly 20y

If Chris has been in business for 20 years, and Chris' strategy has worked for 10 of those years, that means Chris' strategy works 50% the time.

Thus, even if the claims of beating the market for 10 out of 20 years were true, that could be easily explained by random chance.

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#33

Post by wolfman1 »

henning wrote: post #23
wolfman1 wrote: post #15

Earlier quoted context omitted.

Overcrowding an entry on highly liquid assets is something that is so far from reality for our service.

The more highly liquid an asset, the more efficient it is and the fewer trading opportunities after accounting for transaction costs. In something like the S&P 500, everything is already priced in. Meme stocks and shitcoins being manipulated by whales are not efficient and also not as liquid. The larger point remains that none of the above considerations are discussed on this product's page.

I'm realizing there's a lot of confusion about what trend based models actually are. I was under the assumption the concept was more widely understood, but I'm realizing we need to explain it better.

To be clear, there's nothing new or innovative about a trend based model. It's one of the most commonly used investment strategies by intuitions, etc. It's been widely utilized for far longer than I've been alive.

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#36

Post by HenryBemis »

wolfman1 wrote: post #35
helsinki wrote: post #34

If you’re making real money trading, you’re not telling people about it.

What about Hedge funds?

They want _your_ money as well as their profits, because they will charge you some nice fees irrespective if 'this year' was profitable or not.

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#37

Post by wolfman1 »

HenryBemis wrote: post #36
wolfman1 wrote: post #35

Earlier quoted context omitted.

What about Hedge funds?

They want _your_ money as well as their profits, because they will charge you some nice fees irrespective if 'this year' was profitable or not.

The fees are no joke

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#38

Post by dataviz1000 »

helsinki wrote: post #34

If you’re making real money trading, you’re not telling people about it.

I set out on a journey to learn quantitative trading based on signals. The first thing I did was study linear algebra, calculus, statistics, probability, and deep learning. Four months in, I’m on chapter 11 of a deep-learning time-series forecasting book, working through the problems when the author mentions that, to date (it has changed since), there hasn’t been a published paper proving deep learning works better than traditional statistical analysis—i.e., everything in scikit-learn. That sucked.

So I moved on to the next step. There’s an industry that generates hundreds of millions of dollars in ad revenue from blogs and videos on how to trade. For several months, I tested each of these strategies using a backtesting library, vectorbt. People had blogs and videos about using XGBoost and LSTM with other deep-learning libraries—every single one failed.

There’s so much BS in the industry, and I got sucked into the rabbit hole. At least I’m honest enough not to take advantage of other people. Maybe I’ll start a YouTube channel where I backtest every strategy to show everyone that they all fail—and explain why.

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#39

Post by wolfman1 »

dataviz1000 wrote: post #38
helsinki wrote: post #34

If you’re making real money trading, you’re not telling people about it.

I set out on a journey to learn quantitative trading based on signals. The first thing I did was study linear algebra, calculus, statistics, probability, and deep learning. Four months in, I’m on chapter 11 of a deep-learning time-series forecasting book, working through the problems when the author mentions that, to date (it has changed since), there hasn’t been a published paper proving deep learning works better t…

Anything that is related to HFT or day trading is almost impossible in my experience as well. The big funds can do it but I dont think retail has a chance with these approaches.

Have you researched trend or stage analysis? They're slower strategies and dont offer the get rich quick hype, but they do have far better success when done well.

Re: Show HN: TrendFi – I built AI trading signals that self-optimize

#40

Post by wolfman1 »

wolfman1 wrote: post #39
dataviz1000 wrote: post #38

Earlier quoted context omitted.

I set out on a journey to learn quantitative trading based on signals. The first thing I did was study linear algebra, calculus, statistics, probability, and deep learning. Four months in, I’m on chapter 11 of a deep-learning time-series forecasting book, working through the problems when the author mentions that, to date (it has changed since), there hasn’t been a published paper proving deep learning works better t…

Anything that is related to HFT or day trading is almost impossible in my experience as well. The big funds can do it but I dont think retail has a chance with these approaches. Have you researched trend or stage analysis? They're slower strategies and dont offer the get rich quick hype, but they do have far better success when done well.

Btw I think your YT channel would be a good idea.
Post reply on HN