Backtest Price Chart
Run the gauntlet to generate a price chart for this strategy.
▲ entry
▼ exit
price
trending up
trending down
choppy
volatile
unclassified
Backtest Trade Blotter
From the gauntlet's own backtest run — distinct from the Trades tab's live executed trades. Click a row to highlight it on the chart above.
Run the gauntlet to generate trade history for this strategy.
DSR
—
PBO
—
Sortino
—
OOS%
—
Profit Factor
—
Sharpe
—
Win Rate
—
Total P&L
—
DEMO DATA
Equity Curve
Cyan = strategy equity · Dashed white = high-water mark · Red fill = drawdown period · Purple = buy & hold benchmark
DEMO DATA
Monthly Returns Heatmap
Each cell = one calendar month. Green = profit · Red = loss · Intensity = magnitude.
DEMO DATA
Rolling 6-Month Performance
Sharpe (cyan) · Sortino (purple) · Win Rate % (green, right axis)
Score Breakdown
Validation Pipeline
Agent Status
Action Distribution (training history)
Q-Values — Last Observed State
Event Timeline
Parameter Sweep — Sharpe vs. Deflated Sharpe Ratio
Each point is a parameter permutation. Your strategy highlighted in cyan. Diagonal = no deflation penalty.
Sharpe Distribution CDF (Bailey–López)
Cumulative distribution of Sharpe ratios across all permutations. DSR = probability the true Sharpe is positive.
Parameter Optimization Landscape — 3D Surface (drag to rotate)
Z-axis = Sharpe ratio. Surface shows how performance varies across two key parameters. Cyan peak = this strategy's configuration.
Sortino vs. Sharpe
Downside deviation penalty vs. total volatility penalty. Points above diagonal = asymmetric upside.
Rolling Sortino (12-month window)
Sortino ratio computed on a rolling basis over the backtest period.
Risk vs. Return
Annualized return vs. downside deviation. Peer strategies shown in grey.
Return Distribution — MAR Threshold
Monthly return distribution. Red line = Minimum Acceptable Return. Area left of line drives the denominator.
Equity Curve Permutations (1 000 simulations)
Each line is a randomized trade-sequence resampling of the strategy's actual trade history.
Final Equity Distribution
Histogram of terminal equity across all simulations. Dashed line = median outcome.
Cumulative Probability (S-Curve)
Probability of achieving at least X% return. Read as: "X% chance strategy beats Y%".
Probability Density Cone — Time × Equity (drag to rotate)
Each time slice shows the return distribution of all simulations at that moment. Cone widens = uncertainty compounds.
Probability of Backtest Overfitting
Loss threshold chart: probability that the out-of-sample loss will exceed a given amount. Lower curve = safer strategy.
In-Sample vs. Out-of-Sample Rank Scatter
Each point is a CPCV partition. If OOS ranks cluster near IS ranks → low overfit. Cluster in bottom-right → overfit.
IS Rank × OOS Rank × IS Return — 3D Scatter (drag to rotate)
Adds IS return as a third dimension. Green = OOS profitable partition. Cluster along diagonal = low overfit.
Rolling Profit Factor vs. Equity Curve
Rolling 6-month PF (right axis, dashed) overlaid on the equity curve (left axis). PF > 1.0 = profitable window.
Gross Profit vs. Gross Loss by Month
Stacked bars showing monthly gross profit (cyan) and gross loss (red). PF = sum(top) / sum(bottom).
Cumulative P&L
Running profit above zero (cyan). Peak-to-trough drawdown below zero (red). Vertical bars = individual trade run-ups & excursions.
Running Drawdown
Drawdown from equity peak at each point in time. Deeper = larger unrealized loss from high-water mark.
Trade Excursions — Run-ups & Adverse
Per-trade maximum favorable excursion (cyan, above) and maximum adverse excursion (red, below).
Risk vs. Return Scatter
Annualized return vs. annualized volatility. Lines show Sharpe = 0.5, 1.0, 2.0. Your strategy highlighted in cyan.
Walk-Forward Window Results
Each bar = one OOS test period. Green = profitable · Red = loss. OOS% = green ÷ total windows.
OOS Return Distribution
Histogram of per-window OOS returns. Right-skew = consistently profitable test periods.
Chained OOS Equity Curve
Equity built only from OOS periods — the most honest backtest line you can draw.
IS vs OOS Return — 3D Scatter (drag to rotate)
X = in-sample return · Y = out-of-sample return · Z = window index. Rotate to see IS/OOS degradation. Cluster above diagonal = strategy generalizes.
—
No trades yet
This strategy has not recorded any closed or open trades.
—
Computing verdict…
Dimension Scores
Weighted composite — Edge 40% · Robustness 30% · Risk 20% · Sample Adequacy 10%
Key Metrics
Findings
AI Post-Mortem Analysis
Ask the AI to diagnose why this strategy passed or failed its gauntlet, and optionally generate a revised version.
DEMO DATA
Regime Exposure & Edge
Trade allocation and return contribution by market regime.
DEMO DATA
Regime Stress Test
Percentile cone (5/25/50/75/95) from regime-conditioned resampling, with the real regime history along the x-axis.
DEMO DATA
Regime Performance
Return contribution per regime — bar length ∝ magnitude.
DEMO DATA
Regime Verdict
Prop Firm Challenge Simulator
Monte Carlo simulation of this strategy's edge against real prop-firm challenge rules. Estimates only, derived from win rate & profit factor — not a guarantee.
Multi-Firm Comparison
Server-side multi-phase Monte Carlo across every active prop firm (Phase T). Incompatible firms are shown, never hidden.
Running analysis…
Outcome
Summary
Challenge Equity Paths
// select a firm and run a simulation
Daily P&L Distribution
Expected vs. Actual
What the gauntlet promised (sealed at validation time) vs. what live trading has actually delivered.
Loading…
Execution Cost Analysis
Distribution of real per-trade delay cost (decision price → arrival price) vs. what the gauntlet assumed.
Drift Event Stream
Daily backtest-vs-live comparison, most recent first.
Loading…
Equity Curve
Live account equity from Alpaca.
Account Summary
Loading…
Open Positions
Loading…
Order History
⚠
Strategy not found
Check the strategy ID in the URL or go back to the leaderboard.