Traders' Roundtable

programming is not a trivial task.. there's a reason skilled developers make a good living.. here in the midwest, where cost of living is cheap, decent/experienced developers make around 80 grand a year ( a good OO architect does a lot better). I dont' know of any developers at my employer that make ...

i coded up a trading platform for myself that does both.. to cover both scenerios I just abstracted out the source of the data feed, and coded up a simulated-order-execution system ("normal" back testing logic - slippage, etc). Basicly I just swap the datafeed to my indicators between either a live ...

ok just did..

I see what the poster was alluding to when he was talking about trading the indicator.. creating a synth position that tracks the indicator is not unlike using options to create synth positions. Imagine trend following something with a price chart as sedate as a 20 bar sma - definately sparked my ...

I'd use a multi-layer perceptitron with a training set that contained winners as well, and use a binary output. Then include input nuerons for things such as momentum, ROC, volume, etc.. let the ANN figure out the weightings of the inputs to arrive at the output. If there is any predicating signals ...

bringing up an old thread like this may be a no-no, so I appologize in advance...

I burned many many hours trying to get an ANN that tested successfully, to no avail.. they either never trained, or those that did never tested well. I eventually put it on the back burner. However, I was thinking of ...

FYI: I just discovered this forum, and I like what I see :) I have never really felt compelled to participate in any others I've come across.

I don't personaly keep any hard and fast rules for my back testing. I look at the resulting equity curves from the tests and see if it looks "OK".. I look at ...