Yea, 1000 bars is an issue as it is not statistically significant but one cannot avoid this issue. Basically APS works the best, similarly to candlestick patterns, on daily data and 1000 bars means 1000 * 7/5 = 1400 days or 3.8 years. More 1000 bars would mean more than 7 years and those patterns were much different back there for different reasons. Using APS with portfolio reduces number of profitable patterns significantly, particularly across non-related markets. However I am talking here about futures and forex, so maybe APS works with stocks (which are considered much less efficient markets than those mentioned) much better. I did not test stocks as I do not trade them. Probably ETF should be checked as well for APS performance. Besides I have previous version of APS and do not know much about the new one. However if I am not mistaken, say for instance, you have C>C[1] then this relation would generate same pattern for both almost doji with 1 tick difference and for very bullish candle. I think without applying some fuzzy logic to what is higher or lower, the outcome will be wrong. I played with PF > 2, PF < 2 just did not interest me, so I guess I had much fewer patterns. This is my subjective point of view, but I follow it as I want to be on a safe side of this road. But for those who stays with APS I really wish it work for you profitably on long run.
hello,
What is the 1000 bars stand for? Is this the number of bars in each file? In other words, what is the length of the history in each file?
I sorted the results you posted and I notice the following
-In 2008 forward, 108 out of the 232 patterns remained profitable (PF >1). Given that this was a disaster year for stocks, I find the results very good. As a matter of fact, extraordinary good.
- In 2009 forward, during March of this years FTSE index touched 3500, its lowest level in many years. Yet, 102 out of the 232 patterns remained profitable. This is remarkable given that most of the patterns are "long".
Most funds, trading systems, discretionary traders, etc. lost money in 2008 and in the first quarter of 2009. Except if you are doing these tests to find out if APS would have made you rich in 2008.
Another thing: what would be the combined P/L had you traded all these patterns, (although that not make any sense)?
Ron