Search results

My CL system is running live from an SVM resuits. What I did for the KC system, was take the trades from Collective 2 arabica system Throw Massive silicon power on it, select the best models that resembles the strategy output. then use those as my initial population, then run SVM + GP on it...

Positive no over fitting, only 3 parameters. No futures data used. Intra day data used. 32 Xeon cluster running non stop for 28 days with custom SVM and GP. using 512GB RAM I'll give you an example of what is overfit on my next post

lol can't you two guys request your respective private bankers to issue a POF and post it here to settle this. but yeah evoque is a bit crammy for anyone over 6 foot, mostly a soccer moms car.the new porsche macan suv is a bit more roomey.

j just a quick question dom, are you only using price patterns for your system or a variety of indicators ?

This is why a The algo bots are using NLP to intreprets tweets and news headlines. whenever the journalist had a typing snafu, you can catch the hilarious results in the financial market. So if somebody hacked twitter and changed bloomber tweet too US DEFAULT there will be some fireworks.

when u say arb do you mean mostly box spread type arbitrage ?

some money managers that i,ve met ex morgan stanley and etc are more into equities picking. they dont understand futures nor options trading at all

you options trader are like magicians to me. what backtesting solution do you guys use ?

ok, which period do u want to test for downtrend and choppy ?

yeah im thinking of grouping one or more candles but it gets tricky. thx for thr info

I remember a certain forex battle between downpruf and xeelite777, so who won ?

your saying women don't need whores ? or that women cant handle drugs. how sexist of you

Take that 400$ and spend it on Hookers and blow instead

Here is the cluster on 5 minutes on RTH only 8.30 to 15.00 hence the gap 11 - 13 Aug 2014 Prop table 1 2 3 4 5 6 1 30.000000 18.750000 27.500000 16.250000 2.500000 5.000000 2 27.777778 16.666667 22.222222 22.222222 11.111111 0.000000...

Ah, you are thinking like an engineer building a car or plane. Prototype testing in trading can be relatively cheap compared to what your time is worth. Since its not low latency just risk a few hundred bucks to get an early feel of live market behaviour.

Don't you recognize the chart style ? it's just using standard R with quantmod. No big Red bars ever follow another big red bar, maybe a non directional play with options combo might be in order for the NQ on a big down day. Yes I'll run it on a longer time frame, but first I'm running it now...

Oh yeah one more conclusion by looking at the probabilities table. A Big Red Bar is never followed by another big red bar, so BTFD ?? at least since 2012

Heheh yeah "Art". Will do that. I did scale the variables though.

Well I'm not saying you're wrong, in fact I tend to agree with you. I guess we'll have to wait until OPs system go live to see whether non low latency book trading is possible. I think that should be a priority for the OP, test his prototype system in the live market ASAP before fiddling...