Fully Automated - LIVE Trading - $50k per month

[Millionaire]

Might be some bugs with the Twitter integration, but the system should start posting live future trades tomorrow morning.

https://twitter.com/AlphaStratLab

Why don't you concentrate on upping your game and trading mini contracts instead of micros.

You would make 10x the profits you currently do for the same effort.

Make hay while the sun shines.

Instead you are going to post your signals on Twitter. This doesn't make any sense.

 

[globalarbtrader]

Background

I currently have 448 independently trained strategies focused on the 4 micro contracts listed above running live. Half of those strategies can "swing" meaning hold the contract for up to 21 days, while the other half are pure day trading strategies and are flat by market close. The strategies are evenly divided between long and short.

Strategy Generation

I have 7 r5.8Xlarge boxes running at AWS constantly training new strategies...

Each week I plan to train a new stock

Goals/Journal Discussion

I have 3 primary goals for starting this journal:

#1 I am bored... everything is automated, even the strategy generation for the most part. Takes only a few minutes of manual work each day to sanity check new strategies. I am looking for this journal to provide something to do.

#2 To show what is possible with a fully automated system and hopefully inspire others.

#3 To get ideas on which stocks/markets I should train strategies on next - also to discuss best ways to trade those markets.

This should be I interesting...

GAT

 

[frostengine]

Why don't you concentrate on upping your game and trading mini contracts instead of micros.

You would make 10x the profits you currently do for the same effort.

Make hay while the sun shines.

Instead you are going to post your signals on Twitter. This doesn't make any sense.

I am building up to minis. For the number of trades/contracts open at a time, I need a significantly larger account.

As far as posting to Twitter. Figure with nearly 450 independent strategies, the signals will look like noise - so little risk in someone reverse engineering the strategies. However, the extra eyes on the signals may yield interesting observations. If not, i'll stop posting.

 

[frostengine]

Am I reading this right? Less than 1% over all instruments? I suppose this compares very well with what Jim Simmons seems to say in his book about a 51% win rate, which I guess would translate to a 1% expectancy. This was of course sufficient for him to make billions.

Also, and excuse this uninformed question, but since its ML, will the system get better over time? A ML system that teaches itself how to drive I would image gets pretty good with each additional day on the road. Or is the market such that whatever it learns from one day can't be applied too easily to the next?

No, a .25% expectancy means every trade taken has the expectancy to make a .25% gain. Some trades might make 1%.. some trades may lose .5% etc.. but overtime it averages out to a positive expectancy of .25% per trade. What you are referring to is win %. My win% is roughly 67%.

 

[frostengine]

Looks like the twitter posting is working - might have some throttling issues - but appears to be posting.

 

[Concinnity]

Why don't you concentrate on upping your game and trading mini contracts instead of micros.

You would make 10x the profits you currently do for the same effort.

Make hay while the sun shines.

Instead you are going to post your signals on Twitter. This doesn't make any sense.

I mean depending on your lifestyle, though right? for most people that are well adjusted, 50k a month is well beyond the threshold needed for content / not to be unhappy due to financial stress and etc.

So, why not use a larger account and trade smaller size. Much less risk, stress and etc. Obviously if he has bigger ambitions and etc he will need to step it. But going for micro's to mini's is an increase of 1000% in your sizing. That would be my perspective / thoughts, but obviously not everyone is the same I understand that.

 

[NoahA]

Its interesting watching your system work. Its clearly highly profitable, but I also see some trades are held for quite the drawdown. Overall though, the profits certainly don't lie.

I see you started previous threads before on this very same topic of running your strategy. How did those turn out? The previous one just fizzled out but no mention of the long term viability.

Edit: I should clarify that by "quite the drawdown" I mean about 20 NQ points that I saw for some trades. Many trades of course capture much more than this in profits, so the DD isn't extreme IMO. And the last few entries have been absolutely stellar. Anyone following along could absolutely make money taking your trades.

 

[M.W.]

It appears to be a mean reversion strategy. Good luck, your Holy Grail Portfolio Strategy apparently blew up which was also more mean reverting in nature I assume (though have not looked at closely). Perhaps that is why you moved into the higher frequency space?

 

[frostengine]

Its interesting watching your system work. Its clearly highly profitable, but I also see some trades are held for quite the drawdown. Overall though, the profits certainly don't lie.

I see you started previous threads before on this very same topic of running your strategy. How did those turn out? The previous one just fizzled out but no mention of the long term viability.

A lot of strategies discussed in previous threads are still used today. However, a lot of previous threads were using options for the executions - which had too much drag. With that said, the number of strategies have ballooned up significantly over the past 3 or 4 months. Really honed in a process for generating new strategies and I have been expanding very quickly.

 

[frostengine]

It appears to be a mean reversion strategy. Good luck, your Holy Grail Portfolio Strategy apparently blew up which was also more mean reverting in nature I assume (though have not looked at closely). Perhaps that is why you moved into the higher frequency space?

Overall, I would not say my strategy is mean reversion. I have nearly 450 independently trained strategies. Each identifying "different" characteristics of the market. Some are mean reversion, some are trend following, some I frankly don't know what the hell they are doing. Almost appears random - but when they are all put together I have a very smooth equity curve.