Here’s a good example of the deep versus wide approaches.
This is a strategy I’m working on, and I’m trying to decide which version to go live with.
My approach to backtesting is always the same – start with no filtering, then use the Strategy Cruncher to figure out which trades to remove (without curve-fitting).
All these versions correspond to the same entry signal, but in each subsequent version, I’ve used the cruncher to add a rule to remove the poorest trade set.
So, version 4 is a subset of version 3, which is a subset of version 2, etc.
Using only this information, which one do you think is best and why?
Version 1:
- Profit Factor: 1.87
- Win Percent: 53.8%
- Trades: 3,859
- Trades per day: 3.3
Version 2:
- Profit Factor: 3.29
- Win Percent: 55.1%
- Trades: 1,619
- Trades per day: 1.4
Version 3:
- Profit Factor: 4.65
- Win Percent: 63.2%
- Trades: 427
- Trades per day: 0.4
Version 4:
- Profit Factor: 7.59
- Win Percent: 72.6%
- Trades: 106
- Trades per day: 0.1
-Dave
P.S. Are you interested in creating your own strategies? If you’ve got a backtest, you owe it to yourself to try the Strategy Cruncher.
Here’s what one user said recently about it:
Matt: “By using the Strategy Cruncher, I can very easily find the very best filters for any type of strategy backtest without being concerned about over-optimization. Last week, in a mean reversion strategy, in 4 iterations of the cruncher, I found filters that reduced drawdown and increased overall profit by 10x.”
