Welcome to NexusFi: the best trading community on the planet, with over 150,000 members Sign Up Now for Free
Genuine reviews from real traders, not fake reviews from stealth vendors
Quality education from leading professional traders
We are a friendly, helpful, and positive community
We do not tolerate rude behavior, trolling, or vendors advertising in posts
We are here to help, just let us know what you need
You'll need to register in order to view the content of the threads and start contributing to our community. It's free for basic access, or support us by becoming an Elite Member -- see if you qualify for a discount below.
-- Big Mike, Site Administrator
(If you already have an account, login at the top of the page)
For educational purposes, I'm posting these screenshot to compare the performance characteristics of our two NN strategies. If you look at our previous posting you'll see that NN_TRIX was operational during the FED news; so was NWA_ES_R3. NN_TRIX uses no stop; NWA_ES_R3 has a 10pt stop.
You can see that even with a 10pt stop; the market ticks through the position and then eventually reverses to well above it's entry. Look at screenshot two - after an awesome short trade it stops out but goes to a very nice LONG.
It has me completely revisiting the use of stops. Thankfully, NWA was quick to reverse to a long in both cases.
A couple of questions:
a) Does it make more sense to set only a catostrophic stop(ie flash crash); what is a catostrophic stop - 2 days worth of trading profit?
b) If you just got spanked for 10 points would you have the guts to re-enter like the neural strategy?
I think that I'm gaining a better understanding of trading psychology ....
a) Commission 2.4/side; slippage 0 - the trades are market orders.
b) These are neural strategies, right? So, they are trained(not over trained) using recent market conditions with a walkforward period. When a model demonstrates satisfactory performance in both ranges, we paper trade the model so we can better understand its performance characteristics. When comfortable, we live trade it.
c) So how can you avoid using a model, when its no longer performing? Let's start with your curve!
Our models were trained on approximately 2 months of data starting 9/27 back. If you look at your curve, you'll see the model performed nicely(approx 900 Trades); then it saw an ugly cycle(approx 900 Trades); and now it has started backup again.
To avoid the ugly dips, we recommend that traders use performance statistic provided by their software; in your case TS. ie model's equity curve based on 900 trades falls outside - 1.5 std deviations; max losers breached; max drawdown breached; degradation of hit rate. These may be early signs of strategy degradation.
Here's the (5) year equity curves for NWA_ES_R3(Black);NN_TRIX(Red). You can see the dip indicated in your curve on these curves.