When you have AI create an EA, market judgment is split into Python and actual order execution into MQL5. I hit three unexpected snags while connecting these two. The root cause wasn't the "speed" ...
Even with the same strategy, one year shows a PF of 2.07, while another shows a PF of 0.26. This is not about different methods. These are figures obtained by simply breaking down the same settings ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results