AlgoDesk
Live Simulation Desk —
Price · SMA(20) · Bollinger(20,2) · trade markers — live tape scrolling right

ML Signal Engine

triple-barrier · purged CV · calibrated
◌ deep model — training…
P(up)
AUC (ranking)
Log loss
vs prior
Est. Accuracy
Baseline
Brier
Learns from history →
Calibration — predicted vs actual

Order Blotter

live fills, newest first
TimeSidePriceP&L

Opportunity Scanner

whole universe ranked by ML conviction · live · click a card to open it

Risk Cockpit

One book across every desk — deployed exposure, concentration, and the daily-loss circuit breaker. Identical in sim and live; the same breaker and kill-switch guard a linked account.

RSI (14)

70 / 30 bands

MACD (12,26,9)

histogram + signal

Equity Curve

recent history · strategy gated by ML confidence · $10,000 start

Evidence

why the signal says what it says · whether the estimate held · and that the record can't be edited

Logit decomposition of the current signal — which timeframes moved it, and the ledger hash it commits to.

Technology demonstration — synthetic data, not investment advice.
Tickers are real companies, but the price movement shown is simulated, not live market data. Signals come from an ensemble (logistic + small MLP) over multi-timeframe and cross-sectional features, trained in-browser on triple-barrier labels with purged, embargoed walk-forward validation and Platt-calibrated probabilities; entries pass an expected-value gate. Results show the engine's mechanics and discipline, not a proven market edge — on synthetic data they demonstrate method, not alpha. Broker connectivity is a separate, secured layer.