Search results

I think you are the one that misunderstood me. What I meant is: what method did you use to know that you are profitable? I don't think it's possible to know in just 5 days. "Accounting" method you say? How does that work - your account has more money than 5 days ago so you are profitable?

Ed Thorpe's articles on statistical arbitrage. One of the first things I found that actually described a legit edge that still worked at the time I was reading it (unfortunately no longer working today but other elements of those articles are still relevant today to someone just getting into...

Which is what? If you said you have been profitable for 10 years that would be one thing. Profitable for 5 days is most likely meaningless (statistically insignificant) unless you are doing HFT and thus can develop a track record of several thousand trades in just 5 days.

How do you know that you're profitable now?

You sound just like the sterling tech support people. You did not answer the question at all. Do you understand the concept of a "crash" as it relates to software systems? Does sterling still crash itself: (1) every time the internet connection is interrupted and (2) once a day, as the 2014...

The question is: Is the current version of sterling able to operate 24/7 without crashing? The version I tried in 2014 was not able to do so. Sterling acknowledged as much via email, even bizarrely claiming that this somehow wasn't a problem.

I'm sure it's been updated, but has that particular issue been fixed? When I contacted them they wouldn't even acknowledge that it was a bug. It was really bizarre.

Did sterling ever end up fixing their shitty software since 2014? https://www.elitetrader.com/et/threads/why-sterling-pro-is-not-suitable-for-fully-automated-systems.287170/

First of all you should have a reason to believe that you can succeed in this business, e.g. you are smarter than average, you are analytical, intuitive, see patterns easily, etc. Secondly if you have put in your 10000 hours and are still not profitable, cut your losses.. trading is not for...

There is no linear relationship between number of variables and sharpe but I use a couple dozen inputs to my return predictors. The stronger edges contribute much more to sharpe than weaker ones. Shelf life is really unknowable in advance. I'm still trading some of the same edges that I found 7...

I see, so the distribution changes quite a bit between the two time periods, that explains most of what didn't make sense to me. Do you think your system also benefits from higher volatility? Regardless, very nice curve, congratulations on your success.

lol there is zero relationship between keeping commissions low and not sending out a couple emails about this to warn people. They send out tons of alerts and messages about other stuff all the time. This was a goof up plain and simple, there is no excuse.

Ah I see. Nah that isn't something that I typically do since in my experience if an edge stops working it tends to just go flat instead of totally inverting its behavior, and there's a chance it can start working again.

You don't need to trade that much to get sharpe over 3. I think you are overestimating it. To get a sharpe of 15+, yeah, you need to trade a lot for that (like HFT). The main thing I do to control costs is just to incorporate them into my models, so that I'm not doing any trades that are...

The dradown of 3.74% seems very, very small and recovery of 3 days seems almost impossibly short for the standard deviation of 0.98% and mean of 0.2%. Your returns must have some kind of positive skewed distribution (not necessarily a bad thing at all :)) did you make most of your money in a few...

I'm not sure what you mean by this. To elaborate on why high sharpe is important to me: it is because sharpe indicates statistical significance of my edge(s). Especially if the edge is developed through data mining instead of some kind of fundamental economic analysis, you need a way of having...

I would feel uncomfortable trading anything less than 4 or 5.. takes too long to see if the edge is still working or not.

Pretty shocking and disturbing that they just went ahead and implemented this without any warning. IB really dropped the ball here.

have to agree with qlai here. arbitech I wonder if the strategies you are trying to trade were modeled with unrealistic assumptions about what kind of fills you can get. If most of your alpha is coming from capturing the spread you are playing the HFT's game and that's unlikely to work out well...

Amazing returns, would definitely invest in this if it was a fund with an audited track record. Only concern is a bit of negative skewness. Graphs based on the last 116 posts where you recorded the weekly PnL after the text "Return on account for the week" (automatically extracted)