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

31–40 of 122 posts

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

#31

Post by rtstreak »

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.

Indeed, backtesting wouldn't help much in stock prediction. It could work for static input data, but many other factors are involved here.

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

#32

Post by rtstreak »

brianwawok wrote: post #26
samfisher83 wrote: post #24

Earlier quoted context omitted.

If he invested less than the monthly profit he it means he making more than 100%. That is pretty insane.

You can make more than 100% going to the slot machine at the casino. The difference between gambling and trading is not that big. Trading has more ways where you can get an edge over the house, but it is not that different from poker or slot machines.

Well, there is a difference. One takes skill, the other takes luck. The success rate in stock trading is directly influenced on your skill.

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

#33

Post by kyleschiller »

Publication bias is a gigantic problem for amateur FinTech.

How many hundreds of engineers tried the same thing and won't get an article on the front page of HN because no one wants to read about mediocre performance? I don't want to sound too skeptical, quantitative HFT is absolutely the future, but if enough people try something that's effectively gambling, some of them are bound to succeed, and those people will get dramatically disproportionate exposure.

EDIT: I do still like this post and the project, the infrastructure is great and it offers insight into something I'm sure many people are curious about.

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

#34

Post by rtstreak »

machbio wrote: post #18
sebyddd wrote: post #11

Earlier quoted context omitted.

Can't disclose the exact capital, but the initial investment was less than the monthly profit.

not to criticize you, but this seems to have no logic - "My bot holds a single position from seconds to minutes (sometimes even hours), which makes it more of an automated trader than a high frequency trader" - so your initial investment was less than 25K$,meaning you would be tagged has Pattern Daily Trader with account freeze for 90 days - how does your Algorithm even work with that kind of investment ? Definitely…

Intrinio does provide data feeds for Indian exchanges as well: https://intrinio.com/data/national-stock-exchange-nse-prices

He said he trained it based on Intrinio, not that he relies on it for live quotes.

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

#36

Post by sebyddd »

machbio wrote: post #18
sebyddd wrote: post #11

Earlier quoted context omitted.

Can't disclose the exact capital, but the initial investment was less than the monthly profit.

not to criticize you, but this seems to have no logic - "My bot holds a single position from seconds to minutes (sometimes even hours), which makes it more of an automated trader than a high frequency trader" - so your initial investment was less than 25K$,meaning you would be tagged has Pattern Daily Trader with account freeze for 90 days - how does your Algorithm even work with that kind of investment ? Definitely…

Intrinio provides data feed for Indian markets: https://intrinio.com/data/national-stock-exchange-nse-prices

As mentioned in the post, I only used it to train the models on, not to get the live quotes for trading.

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

#37

Post by digler999 »

kyleschiller wrote: post #33

Publication bias is a gigantic problem for amateur FinTech. How many hundreds of engineers tried the same thing and won't get an article on the front page of HN because no one wants to read about mediocre performance? I don't want to sound too skeptical, quantitative HFT is absolutely the future, but if enough people try something that's effectively gambling, some of them are bound to succeed, and those people will g…

> How many hundreds of engineers tried the same thing

And you bet your ass if I tried and succeeded I'm not going to come here and brag about it, risking whatever ephemeral edge I had. If I did this, I would do it for dollars, not karma points.

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

#40

Post by sebyddd »

kyleschiller wrote: post #33

Publication bias is a gigantic problem for amateur FinTech. How many hundreds of engineers tried the same thing and won't get an article on the front page of HN because no one wants to read about mediocre performance? I don't want to sound too skeptical, quantitative HFT is absolutely the future, but if enough people try something that's effectively gambling, some of them are bound to succeed, and those people will g…

While I do agree with you to some extent, as opposed to gambling, stock market requires technical knowledge. I strongly believe that individual traders stand no chance agains the big players and there may be a combination of luck + favorable stock picks in this case.
Post reply on HN