- Search Forex Factory
- 23 Results
- flyboy replied Feb 24, 2012
Market microstructure paper. — Some time ago there was a paper posted in this thread on market microstructure, including a simulation of order book, etc. I can't find that paper now, does anyone have a reference to it?
- flyboy replied May 18, 2010
Clutter filters redux. — This thread has been quiet for a while so I figure I'll try to awaken it. We're all looking for a decent clutter filter, so I feel a good first approach is to break down what clutter is. For me, it's three things: 1. ...
- flyboy replied May 13, 2010
Fixed it. It was a coding error on my part. So now I have a decent hull moving average, a sinc filter (with lag) and a butterworth filter (without lag). The butterworth still seems to have more lag than the hull moving average though. PS: does ...
- flyboy replied May 12, 2010
Okay here's the butterworth filter. It tracks very nicely but doesn't smooth terribly well. Playing with the period doesn't affect things at all as far as I can see.
- flyboy replied May 12, 2010
No, as he mentioned this is a butterworth filter. Quite different. But it should be useful.
- flyboy replied May 10, 2010
I don't suppose you know of a simple way to implement polystab? matlab implements it as a matrix, which are difficult to deal with in normal programming languages.
- flyboy replied May 10, 2010
Ahh. I figured there was something I was missing. This looks like great "fun" to implement in java. Thanks Philippe.
- flyboy replied May 10, 2010
sinc filter lag. — Forgive me for dragging up old material. I've just implemented a sinc filter in my trading system, and I've found my implementation has horrible lag. I was under the impression that a sinc filter had low phase lag. Am I ...
- flyboy replied Apr 19, 2010
I don't follow climatology at all, but my ears instantly perk up when you mention it in this forum. We're dealing with almost exactly the same problems. Predicting the (short term) future of a non-linear dynamic system. No doubt they have some ...
- flyboy replied Apr 19, 2010
CB's ULLMA filter is a sinc filter with some other preprocessing applied. He suggests it uses some HA filtering first. But no one really knows. asm8086's ullma filter uses HA with a sinc filter and gives and extremely clean signal. I consider the ...
- flyboy replied Dec 12, 2009
We're not even at the system point here. In this tread we went from promising potential to mostly disappointment. BUT some of us here are taking the right approach - Characterizing our data, and only then moving on to find tools/filters to help ...
- flyboy replied Dec 7, 2009
I'm actually looking at it as inspiration. Overall their approach won't work, but they might have some aspect that sparks an idea. I'm searching as much as I can for anything that deals with non-stationary data and non-linear systems. Someone might ...
- flyboy replied Dec 6, 2009
I found this paper on normalizing non-stationary timeseries. Technically they don't normalize, they adjust a kalman filter in place. It seems like an interesting route and one that's been discussed (but I don't think attempted) by some people here. ...
- flyboy replied Nov 24, 2009
asm8086 is the real Codebreaker!!
- flyboy replied Nov 24, 2009
hah. I wish I was CB!! I'd have his knowledge about signal processing. I'd probably be quite well off by now. Of course, I'd also have his taste in clothing... image I've just been following this thread for quite a while and testing some of the ...
- flyboy replied Nov 24, 2009
Welcome back enigmafx. We're positive CB not only changed his trading methods, but spoke about multiple entirely different trading systems. And some suicidal ones (the pairs trade). Identifying stable periods will be difficult with an fft or ...
- flyboy replied Nov 19, 2009
How does asm8086's ullma+your CF from post #585 perform over time? From what I gather from CB's posts his thresholds weren't adaptive. Instead he convoluted the input - adapted the timeframe realtime rather than adapting his system parameters. EDIT: ...
- flyboy replied Nov 18, 2009
Hi madcow, I'm really surprised if this is what he is actually doing. Perhaps this CB fellow has being toying with us all along? I did ask him specifically about his clutter filter and he gave his goertzel SnR answer. Which his original topcat ...
- flyboy replied Nov 12, 2009
This actually doesn't look like a horrible way to calculate SnR at all. How does it perform in slow moving sideways markets? In fact, that's the first test I'd like to see for any clutter filter. Throw the worst at it from the start.
- flyboy replied Oct 1, 2009
Yes something did happen - they got married. Which is fantastic for them. Congratulations to them both.