@black-magmar in my opinion, both single and multi pass (backtest_ml) are forward looking. Single pass uses all data to train. I also think that backtest_ml is forward looking bcz : although it trains iteratively, it also predicts the period inside the training data. (E.g : according to my understanding, training data period can be choosen as from 2010-2013, and the code predicts from 2012-2013, of course it depends on your choice of training_period and test_period in the para of backtest_ml, but it does predict the period it has been trained on)
-
This topic is deleted!
• online.mr_mime -
This topic is deleted!
• aluminum.dinosaur -
This topic is deleted!
• leather.metapod -
This topic is deleted!
• giant.pinsir -
This topic is deleted!
• jamesanderson07 -
This topic is deleted!
• paulwalker08 -
This topic is deleted!
• SBCGlobal -
This topic is deleted!
• galaxysuper23 -
This topic is deleted!
• dennisking148 -
This topic is deleted!
• roberttaylor -
This topic is deleted!
• leather.scyther -
This topic is deleted!
• rebeccajane -
This topic is deleted!
• pitchnhire542 -
This topic is deleted!
• green.reindeer -
This topic is deleted!
• krishnamishra -
This topic is deleted!
• punarjanayurveda1