> > results of a first little back test run: > used data set: ES-GLOBEX-FUT-200909.txt from the JBT web site > Hardware: dual core Intel T2500 @ 2.00 GHz > back test time: ~ 90 minutes > > Results from JBT main window: > Trades: 19 > Net Profit: 2446 > Profit Factor: 7.38 > Max DD: 174 > >
Looks promising, although the number of trades is too low to be statistically significant. To increase the number of trades, you may want to do one or more of the following: a) increase the "difference" threshold from 2 to 4 or so b) decrease the "neighbors" threshold from 5 to 2 or 1 c) increase the "lookAheadPeriod" from 3600 to 7200 or so 90 minutes to run a back test is excessive, of course. This needs to be addressed with a better searching algorithm, as I mentioned before. The other thing is the patter matching as I've implemented is very rudimentary. All it does is that it compares current single indicator value with the past ones. A far better approach would be to compare segments (i.e., sequences of indicator values), as outlined in that paper that you've cited. I'll work on that tonight and repost that sample strategy sometimes today or tomorrow. --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "JBookTrader" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/jbooktrader?hl=en -~----------~----~----~----~------~----~------~--~---
