Demo mode — synthetic historical data

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.

Quant tool

Stress testing

Take your watchlist, regress each ticker against SPY to get β, then apply 5 named historical SPY shocks. Each ticker shock = β × spy_shock; portfolio = equal-weight average.

💡 Plain English: If 2008 GFC, COVID 2020, or the 2022 rate spike happened again, how would your watchlist react? We project per-ticker hits via each one's beta to SPY.

Tickers (comma-separated)

US tickers recommended — the scenarios (2008 GFC, COVID, Volmageddon, 2022 rate spike, dotcom) are SPY shocks. Non-US tickers get a SPY-relative beta which is informative but not the right benchmark for their home market.

Methodology. OLS regression of last 252 days of ticker returns on SPY returns gives β. Shock_ticker = β × spy_shock (α forced to zero). Portfolio = equal-weight average. Scenarios sorted worst-first.

Beta is non-stationary — a 2024-fit β may not reflect a 2008-style regime. Correlations also spike toward 1 in tail events; expect actual losses to be deeper than a beta-only model suggests.

Stress testing

Take your watchlist, regress each ticker against SPY to get β, then apply 5 named historical SPY shocks. Each ticker shock = β × spy_shock; portfolio = equal-weight average.

💡 Plain English: If 2008 GFC, COVID 2020, or the 2022 rate spike happened again, how would your watchlist react? We project per-ticker hits via each one's beta to SPY.