Have you tried removing non-US futures that trade in a different time zone? In my replication that reduced Sharpe to 0.7 meaning there is a lookahead bias from one timezone to another.
Maxim, you were 100% right, thank you! Removing the different-timezone futures and re-learning the graphs takes GMOM from 2.1 to ~1.0, no better than individual momentum: the network edge was timezone lookahead. I've published an update with the full ablation and corrected conclusions. Thank you!
Have you tried removing non-US futures that trade in a different time zone? In my replication that reduced Sharpe to 0.7 meaning there is a lookahead bias from one timezone to another.
Maxim, you were 100% right, thank you! Removing the different-timezone futures and re-learning the graphs takes GMOM from 2.1 to ~1.0, no better than individual momentum: the network edge was timezone lookahead. I've published an update with the full ablation and corrected conclusions. Thank you!