I am currently testing a system for forex. It is beyond my ability to code this system for back testing due to it's complexity. I have therefore traded this system live on a small account. The system trades 0-2 times per day. I've recorded trades for 3 months (about 50 trades). How long does one need to test a system like this before putting real money into it? How many trades should it take and over what period before I can consider the results reliable?
If you are using technical analysis to trade a linear product, with certainty, you can back test it. If it is still "too complex" then your strategy is most likely based on your instinct. Your instinct will change with experience and current mood. Start trading right now with a super small amount of capital, get your reps in. Ps. Trading a 1 lot with real money is 100x better for your development than sim trading.
The rules I use for this system are clearly defined. There is no instinct here, just hard data. What makes this strategy difficult to code is that it trades multiple types of instruments and markets across different time frames. It probably can be coded, but the average bear will not be able to do it.
I am trading this live on a small account. Question is, how many trades are required before I can safely say that the observations are statistically significant rather than luck.
Well you can't really "safely say" because the markets are always changing. You said the strategy makes 2-3% a week right? In that case you provably only need...a month. There are many tools you can use to test the significance. But whats also very important is to find out when the strategy stops working
What I was looking for was a little more "scientific" answer to the questions. A month will only generate a theoretical maximum of 40 trade observations. Realistically, it will generate 20 trade observations. Hardly enough to deem a system safe in my "opinion" ( I never studied deep into stats). I so far have about 50 observations. So the conclusion I have now is this. 1)The more observations the better. 2) Instead of dumping a lump of money into the account, I will probably just add in small chunks of money in every month. Know when the system stops working is the easiest part as I have prior trading stats to compare it against.
When to start trading live..............as soon as possible, but start with a very small account and blow it up couple of times (ofcourse depending on the system as some can blow up in 30 min and in FOREX within 2 min). $500 account using stop and target loss levels with automation would be a good place to start. Sim trading is very different than real trading.
The system is already live for 3 months on a $1000 account. The question is when do you start throwing real money at it i.e. 10k, 20k etc