Cryptocurrencies, stocks, algorithm trading

[Garquillex]

Anyone deal with these things? I remember this board was all over bitcoin's nuts when it was hiking to $1200

It took me far too many years but I realized I could use my immense math skills and interest in theoretical math and programming to make money.

Currently building a variety of bots to trade cryptocurrencies. I've spent a lot of time learning to manually trade with good success rates (did 20-30 trades on Eth in a few hours recently, only lost 1, the rest were 3-10% gains, which is actually sickeningly profitable if I was trading with more)

I have an automated backtesting system in place comparing every combo of indicator variables, but it's janky and I might build my own engine or just deal with it. Not sure how hard the backtest engine could be, might save it for later just to improve already good profits. Or I could find something open source, but haven't yet.

[Dinglesberry]

Re: Cryptocurrencies, stocks, algorithm trading

This could be a good idea.. There's a reason there isn't open source software like this. Major investing firms have software to automate it, without a doubt.

Logically speaking, it's a matter of optimizing it and placing low risk trades - consider, if something has even a 51% success rate, over an infinite number of iterations, theoretically it should tend towards a net gain, if that makes sense.

Is this called the Gambler's Fallacy? Maybe I think if you can optimize your returns enough, you could definitely make money automatically though.

[inDheart]

Re: Cryptocurrencies, stocks, algorithm trading

this is just fantasy sports without the sports tbh

glhf

[xXOpkillerXx]

Re: Cryptocurrencies, stocks, algorithm trading

Why not do machine learning with "predictions" as output and the trades you do manually as dataset. That way you get to learn even more about the params needed for a good trade, and you might even see surprising results in the weights in the end. Just an idea...

[Dinglesberry]

Re: Cryptocurrencies, stocks, algorithm trading

Why not do machine learning with "predictions" as output and the trades you do manually as dataset. That way you get to learn even more about the params needed for a good trade, and you might even see surprising results in the weights in the end. Just an idea...

I dunno, when it comes to something that deals with my money, I don't know if I'd trust a machine to learn based on it's own results.. It's like a machine that learns by reading posts on the FFR forums... Can you imagine what it would post? Ayyyy

[25thhour]

Re: Cryptocurrencies, stocks, algorithm trading

I got the money if you want to split profits once your trading bots are tested more. Lets get rich. I do some Forex trading, and love investing.

[xXOpkillerXx]

Re: Cryptocurrencies, stocks, algorithm trading

I dunno, when it comes to something that deals with my money, I don't know if I'd trust a machine to learn based on it's own results.. It's like a machine that learns by reading posts on the FFR forums... Can you imagine what it would post? Ayyyy

Well that's up to you. If the AI was trained for long enough, there shouldnt be a problem. In any case, it's easy to add a manual confirmation feature to it.

[remedy1502]

Re: Cryptocurrencies, stocks, algorithm trading

I dunno, when it comes to something that deals with my money, I don't know if I'd trust a machine to learn based on it's own results.. It's like a machine that learns by reading posts on the FFR forums... Can you imagine what it would post? Ayyyy

probably something like this

http://imgur.com/gallery/VhlAW

[Dinglesberry]

Re: Cryptocurrencies, stocks, algorithm trading

probably something like this
http://imgur.com/gallery/VhlAW

I'd guess something more like this

http://www.flashflashrevolution.com/....php?p=4458673

[Soundwave-]

Re: Cryptocurrencies, stocks, algorithm trading

Why not do machine learning with "predictions" as output and the trades you do manually as dataset. That way you get to learn even more about the params needed for a good trade, and you might even see surprising results in the weights in the end. Just an idea...

I mean this is basically the point of backtesting, although I'm not sure if traditional machine learning has been applied to it before.

I've wanted to develop some open source procedural trading software, but the problem is to test it well you either need money or market data, neither of which are amazingly easy to obtain.

[igotrhythm]

Re: Cryptocurrencies, stocks, algorithm trading

This could be a good idea.. There's a reason there isn't open source software like this. Major investing firms have software to automate it, without a doubt.

Logically speaking, it's a matter of optimizing it and placing low risk trades - consider, if something has even a 51% success rate, over an infinite number of iterations, theoretically it should tend towards a net gain, if that makes sense.

Is this called the Gambler's Fallacy? Maybe I think if you can optimize your returns enough, you could definitely make money automatically though.

Gambler's fallacy is "the wheel has come up black six times in a row now, so it's DEFINITELY going to come up red next."

But programming bots and getting involved in Bitcoin, especially after the last Halvening? I'd like you to be in my Maki Dev Slack with a bunch of guys that are looking to re-make the Internet and "decentralize ALL THE THINGS." PM me if you want a link.

[FoJaR]

Re: Cryptocurrencies, stocks, algorithm trading

I dunno, when it comes to something that deals with my money, I don't know if I'd trust a machine to learn based on it's own results.. It's like a machine that learns by reading posts on the FFR forums... Can you imagine what it would post? Ayyyy

just have it emulate trades at first, let it run and see how it does with fake money. once you're confident that it works as intended start using real money.

[Garquillex]

Re: Cryptocurrencies, stocks, algorithm trading

Why not do machine learning with "predictions" as output and the trades you do manually as dataset. That way you get to learn even more about the params needed for a good trade, and you might even see surprising results in the weights in the end. Just an idea...

I want to work with genetic algorithms eventually, but I think for now I'm a lot smarter than whatever I can teach a bot to learn (and it could take forever and be difficult to control).

I have like 4 months to make this profitable. I think I can do it by September if I work hard enough.

I got the money if you want to split profits once your trading bots are tested more. Lets get rich. I do some Forex trading, and love investing.

Maybe if you're serious. I only have 1k to work with while having a safe bank account, and a terrible job I may or may not return to on August 26thish.

I'm splitting off into stocks and forex later on to keep up the diversity and reduce slippage.

Well that's up to you. If the AI was trained for long enough, there shouldnt be a problem. In any case, it's easy to add a manual confirmation feature to it.

I spent a few weeks manually trading and I want to get as far away from it as I can, at least when dealing in a 24/7 market. You have to close out trades or never sleep, or risk losing money while you sleep. I just never slept. Except for sleeping through every single bitcoin price drop so far. Now I have an auto-sell to USD system in place that also plays loud music to wake me up.

I mean this is basically the point of backtesting, although I'm not sure if traditional machine learning has been applied to it before.

I've wanted to develop some open source procedural trading software, but the problem is to test it well you either need money or market data, neither of which are amazingly easy to obtain.

Bitcoin market data is easily available. It's the natural place to start considering you apparently legally need $25k in an exchange account to be a day trader.

Only problem is they only have it available in 1 minute chunks, which is usually fine, but a really good bot reads live order books too, which makes backtesting that logic essentially impossible without an enormous effort.

But programming bots and getting involved in Bitcoin, especially after the last Halvening? I'd like you to be in my Maki Dev Slack with a bunch of guys that are looking to re-make the Internet and "decentralize ALL THE THINGS." PM me if you want a link.

What's this about?

[Garquillex]

Re: Cryptocurrencies, stocks, algorithm trading

I wonder what the bitcoin price would be if bitfinex didn't keep fucking up the market

[xXOpkillerXx]

Re: Cryptocurrencies, stocks, algorithm trading

I want to work with genetic algorithms eventually, but I think for now I'm a lot smarter than whatever I can teach a bot to learn (and it could take forever and be difficult to control).

You do realize that all you can make your program do, you can put it in a deep learning algo right ? I mean, if done right, the learning AI should Not yield lower results than the base settings you give it. But yeah, you gotta know that stuff fairly well ofc