Search results

Your assumptions are based on technology that is publically available and in wide-spread use, hence your dismal perception of neural nets. All of the publically available and widely used models of neural nets are silly hacks that really have no relation to how brains recognize patterns and...

Theoretical physics and models of cognition and perception, this is somewhat related to agent-based modelling which is another pretty exciting field but I believe the wrong approach.

Where is your server located and how many hops away is it? tracert or traceroute can tell you this. 100ms is just absurd, I get 40ms to Lime on a bad day from my colo in austin, when i relocate to the same colo in NY the ping will be between 1 and 5 ms.

You'll always see multiple quotes from INET if you are subscribed (as is nearly everyone). If you see multiple quotes from non-ECN market makers then you'll have totalview.

Depends on your broker/software, but there should be an option in the order properties. For instance, with Lime, you set AllowRouting=true "(currently only available for ARCA, default is false). Allow the order to be re-routed from the specified route to the source of the NBBO for...

Eh, what are you defining as AI? Because statistics and AI are the same thing, but "AI" is just statistics that is much more complicated than what most people perceive statistics to be.

I use the term 'think' loosely, but I am somewhat inspired by On Intelligence. <-- dont expect anything really technical there. By thinking, I mean, not making model assumptions about the data. Using the latest nonparametric methods to infer structure from the data. That is learning, or...

lol. Well it's myself driving the deadlines (for my trading adventures). Deadlines for work, I don't care that much about, working for a salary is for suckers. I wouldn't suggest anyone become a programmer these days if you have the capital to hire someone. But yeah, sauna/massage is...

Right, you might also look into taking offseting positions in the index vs. the components you are holding so as to hedge against sector specific risks, although you'd still be exposed to market wide drift.

I wouldn't advocate putting any hard cutoff points in your calculations (like 0.60), because by doing that you are introducing bias beforehand with no real theoretical justification, and also no way to indicate to your model the level of uncertainty of your 0.60 value. I don't have any...

When talking about correlation, you have to define the time scale you are referring to. Moving intraday correlation? Daily closing price correlation? Usually things that are weighted together in an index are highly correlated, so I'd say your answer is 'both'.

Thanks for the reply. Fascinating, is there varying dosages? I don't want to completely wack out my schedule but sometimes I'm on a 'roll' so to speak and my productivity is flowing so well I don't want to stop, cause a lot of good stuff is missed by the start up and slow down time. E.g, the...

haha, don't quit your day job. :p Although you are probably right, I haven't been posting much lately.

The smallest indivudal you knew was trading 2.5 mill? How much did he start out with? I would think you only need the 25K PDT minimum unless i'm missing something. Also, these blow ups sound interesting. Is hedging not so common for intraday bots? Were they just leveraged so far that a small...

:D Hmm, wonder what the weather's like tomrrow?

Hah no, I thouroghly enjoy sleeping but I've been working mad hours and then spending the rest of the time on system development and that leaves little time for sleep. It's just that when I'm awake, I want my mind to be as sharp as possible. I already do obvious things like working out/running...

Anyone have experience with this? Good, bad, indifferent?

"Start to get filled?" Eh, i'm not following you. There is a very specific and real chance that all of the orders get filled instantly, and your defintion of "real quick" can never be fast enoguh.

Heh, I think before you decide to do that, you need to analyze the payoff vs. risk. Is your better fill worth it when taking into account the double-execution risk? That is the question you need to answer.

What timeframe are you working on? I backtest with 1-second intervals with full depth of book data. My system gives immediate recommendations and I only trade high volume issues and I do realtime trading decisions (e.g. i dont optimize parameters ahead of time) and I always simulate limit orders...