Backfilled 90-day predictions for all 13-market seed tickers using a momentum-based synthetic signal. Not the live model's output — this view shows what the analytics WILL look like once the real predictions_log has accumulated. Real-data view at the link.
Walk-forward + Monte Carlo
Two rigour checks that defang the in-sample bias of the alpha and factor analyses. Walk-forward splits the prediction history chronologically and tests whether the signal is consistent fold-to-fold. Monte Carlo bootstrap resamples cohort returns 5,000 times to estimate the distribution of final equity, max drawdown, and Sharpe.
💡 Plain English: Is the model's edge steady over time, or did it get lucky once? We chop history into chunks and test each. Then we resample 5,000 times to see the full range of possible outcomes.