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

Neural Net Side Project Makes $3500/mo Trading Stocks

indiehackers.com

Post reply on HN
Print view View original

51–60 of 122 posts

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#51

Post by dollar »

csallen wrote: post #41
dollar wrote: post #39

I wonder how many engineers have replicated the payoff of a dynamically hedged short option without understanding that was what was happening.

You should explain for those of us who know little about finance but are curious!

There are volumes written on this subject, though Taleb's "Dynamic Hedging" is as good an introduction as any. The short explanation is that, in theory, the payoff of any vanilla option can be replicated by trading the underlying asset. For a while, quite a long while even, this kind of trading can look profitable. There are many variations on this, such as trade frequency and holding interval, but in the very end you realize you are being compensated for an asymmetric risk. That is the risk of sudden changes of price while you happen to have a position open, among many other risks. I would say that 99% of the "newly discovered" profitable systems I have seen over the last 20 years were unwittingly replicating a short vanilla or exotic option without understanding the risk.

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#52

Post by alva »

Reposting my comment on the first HN submission of this page

"The claims made in this interview are extremely suspect, it just not make sense. Absolutely no relevant details are included. The developer claims he was able to built an AI trading strategy that is profitable 95% of the time. No technical details about the strategy or platform for trading is provided. A few trading buzzwords thrown in a few places. The rest of the interview is platitudes and inspirational hacker talk

I think IndieHackers needs to investigate the claims and be provided proof, otherwise this appears to be a fake project for the developer's own publicity. If IndieHackers are fine with that, I will stop visiting as I cannot trust that the content is not just shallow, exaggerated claims to raise peoples profiles."

After expressing my concerns directly to IndieHackers, the interview was changed in multiple places to flesh out a number of the spurious claims which I had criticised.

Without further details or some proof from the developer, this piece stinks. Taking into account the rest of the interview which contains stereotypical inspirational hacker talk, the whole thing feels like a badly done promotional bit for SV style status.

If I am wrong, I will apologise and the developer is going to be a multimillionaire very, very quickly. Until there is more details, I am going to be totally sceptical of IndieHacker interviews going forward. Which is a shame as I think IndieHackers is a great site. How can I trust that the other submissions are not baseless, PR pieces?

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#54

Post by perteraul »

_jgvg wrote: post #48

Sorry, but the little content available on the page, the Amazon ads and the very short run time makes my BS detector sound like an air-raid alarm. Do you have anything beyond "I'm making $3.5k using methods I won't disclose on an initial investment that I won't disclose"? What's your return on your investment? Sharpe Ratio? If you apply your investment criteria in historical data, do you beat the market? How differen…

If you had created something that works for you, would you sell out all the details by spreading it on a public blog?

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#55

Post by ucaetano »

perteraul wrote: post #54
_jgvg wrote: post #48

Sorry, but the little content available on the page, the Amazon ads and the very short run time makes my BS detector sound like an air-raid alarm. Do you have anything beyond "I'm making $3.5k using methods I won't disclose on an initial investment that I won't disclose"? What's your return on your investment? Sharpe Ratio? If you apply your investment criteria in historical data, do you beat the market? How differen…

If you had created something that works for you, would you sell out all the details by spreading it on a public blog?

None of the details I asked would give his strategy, would only prove his success.

Hedge funds, for example, are largely black boxes, but the publish their returns.

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#56

Post by minimaxir »

Votes on this submission may be manipulated with an attempt to bypass the voting ring detector via linking to /newest: http://i.imgur.com/08pAFOw.jpg

And another one by Indiehackers founder csallen after it already hit the front page: http://i.imgur.com/rxWtsWJ.jpg

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#57

Post by sgt101 »

hmate9 wrote: post #47
brianwawok wrote: post #27

Earlier quoted context omitted.

Backtesting does not mean much. It's easy to make an algo do well yesterday. Very hard to make it do well tomorrow.

I completely disagree. Backtesting matters, especially in HFT. What would you rather have: an algorithm that has performed well on 5 years worth of historical data or one that has performed well in the past 2 weeks.

Neither; these are techniques applied on observed data in an obviously dynamic open domain. The data is uncontrolled - so we have no idea if it is representative of the current state of the domain theory - does it cover the distributions properly; we don't know. We know the domain is dynamic in that the world economy moves like around alot and we can't predict these movements, in the sense that most actors did not call the last substantial negative market movement. The domain is open in that new features can appear that drive the value of the variable of interest; for example the availability of property in China, new battery technology, a patent on nuclear fusion.

We do not have techniques that account properly for any of these things.

You may as well draw lines on charts and sell that advice, you'd probably get as good a hearing in any Investment Bank in the world !

oh....

wait...

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#58

Post by tunesmith »

brianwawok wrote: post #27
hmate9 wrote: post #22

I do not wish to be negative, I just think it is very hard to really judge this system without knowing the technical details behind it. Since we are currently in a bull market it could just be a fluke. I did not read anything about backtesting. Have you done that? If so, I take it back :)

Backtesting does not mean much. It's easy to make an algo do well yesterday. Very hard to make it do well tomorrow.

Does backtesting work better if you, say, start with seven years of data, use the first five to judge the strategy, and then test it against the last two? Is that a good way to avoid fitting the data?

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#59

Post by svantana »

I may be way to cynical for my own good, but there's no proof that this is actually real, right? Besides a couple of pretty bizarre screenshots [1]. I'm skeptical because a) these types of gains in public markets are pretty much unheard of, and b) faking a story like this would be a fairly easy way of getting lots of attention for your freelancer business (which this guy advertises right at the top of the article).

[1] Running cat on a csv file would usually just print a list of numbers, yes? Instead he gets ascii art with months on the vertical axis, making it seem like time going back and forth, and some random commentary in the right margin. I dunno but something about it screams "mockup". As does the minimalist, ultra-stylish AWS window.

Edit: also, if it were me who got incredible returns from trading at high speed on indian markets using only machine learning on historical data, I would definitely keep quiet about it. Just sayin'...

Re: Neural Net Side Project Makes $3500/mo Trading Stocks

#60

Post by ucaetano »

alva wrote: post #52

Reposting my comment on the first HN submission of this page "The claims made in this interview are extremely suspect, it just not make sense. Absolutely no relevant details are included. The developer claims he was able to built an AI trading strategy that is profitable 95% of the time. No technical details about the strategy or platform for trading is provided. A few trading buzzwords thrown in a few places. The re…

Do you have a link to the original version? It looks fake enough as it is, I wonder how much bad it could be.

But hey, maybe this guy really cracked the market, and a Nobel prize and billions of USDs are on the way...

Post reply on HN