// Platform

Backtesting

Falcon AI runs three engines across six modes. RAPTOR and TITAN are the same core strategy tuned by timeframe on MNQ, each in your choice of session window (PRIME / EXTENDED / GOLDEN), plus an Elite-exclusive Gold GLOBEX mode. TALON and SAKER are separate engines with their own logic. RAPTOR and TITAN share IDENTICAL risk math and differ only by timeframe and session window. The backtests below cover the MNQ session modes. Exact multipliers and confluence thresholds ship to active subscribers via the Settings Vault (pre-tuned per tier, ready to trade). We don't sell backtests. We sell what we trade. Every core mode trades live and is published daily on our results page. RAPTOR · GOLDEN was the first tier live-broker validated, on our personal NinjaTrader account (real money): 62 trades in the 10am–1pm window, PF 3.13, 88.7% WR, +$2,582 across 5 days (May 11–15, 2026) — live beats backtest 2×. Since then we passed 5 prop-firm evals — 4 Topstep + 1 Apex — across June 8–11, 2026 (certificates published); all core modes now run live across our Topstep accounts.

Platform Documentation · Updated May 2026 · Results are hypothetical

01Methodology

The Falcon AI backtesting methodology applies the live signal engine logic retroactively to historical bar data, recording every signal that would have been generated and its subsequent outcome based on whether price reached the take-profit or stop-loss level first.

Data Source — CME historical tick and OHLCV data as provided through TradingView's data feed. Data quality and availability vary by contract and time period.
Testing Period — 30-min modes Jan 2024 → Jun 2026 (~30 months); 15-min modes Aug 2025 → Jun 2026 (~11 months, TradingView's 15-min data depth) — Bar Magnifier enabled. Spans the 2024–2026 cycle of Fed rate cuts and consolidation. RAPTOR · GOLDEN was the first tier live-broker validated on our personal NinjaTrader account (62 trades in the 10am–1pm window, May 2026).
Instruments Tested — MNQ (30-min primary across TITAN · PRIME + TITAN · EXTENDED; 15-min RAPTOR · EXTENDED variant). RAPTOR · EXTENDED is our recommended mode (best live return-to-risk) and, like every core mode, is traded live with results published daily; the 30-min modes show the cleanest backtest drawdown. Secondary testing on Gold (COMEX:MGC1! — Micro Gold futures, 30-min, GLOBEX session (around-the-clock), Elite-exclusive — backtest only, not yet live-validated).
Entry Assumption — Signals are recorded as entered at the open of the bar following signal confirmation, representing the first available execution opportunity.
Exit Logic — The trade closes on whichever of the strategy's exits is reached first within the signal's validity window. The exact exit rules and parameters ship to active subscribers as part of the Settings Vault, pre-tuned per tier. All other parameters are identical between timeframes.
Signal Filtering — Only signals at or above the engine's default minimum confluence threshold are included in the backtested results, consistent with what the live indicator displays out of the box. Exact threshold values are shipped to active subscribers via the Settings Vault.

02Performance Metrics

The following metrics are tracked and displayed in the Falcon AI performance dashboard, accessible to subscribers via TradingView's strategy results panel:

Win Rate — Percentage of signals that reached TP1 before stop-loss. A secondary win rate to TP2 is also reported.
Total Trades — Count of all signals taken during the backtest period, used alongside win rate to evaluate sample-size confidence in the results.
Maximum Drawdown — The largest peak-to-trough decline in the hypothetical equity curve, expressed as a percentage of starting capital.
Sharpe Ratio — Return per unit of risk, annualized. Calculated using daily P&L under fixed 1% per-trade risk assumptions.
Profit Factor — Gross profit divided by gross loss. A profit factor above 1.0 indicates a net-positive strategy; above 1.5 is considered strong.
Consecutive Losing Trades — Maximum number of back-to-back losing signals recorded during the test period. Important for evaluating psychological and capital drawdown risk.

03Key Results

The backtests below cover the six MNQ session modes: RAPTOR and TITAN, each across PRIME, EXTENDED and GOLDEN. They share IDENTICAL risk math and differ only by timeframe and session window. TALON and SAKER are separate engines and are not included here. Backtests below are on TradingView Strategy Tester (Bar Magnifier ON, ATR risk-based sizing (cap 2 contracts), $100K account, $1.50 commission/side, 1 tick slippage, default minimum confluence threshold applied — same as the live indicator). RAPTOR · GOLDEN was the first tier live-broker validated on our personal NinjaTrader account (62 trades in the 10am–1pm window · PF 3.13 · 88.7% WR · +$2,582 across 5 days, May 11–15). We now run all core modes live in our own Topstep accounts.

The 8 MNQ Tiers + Gold Elite-Exclusive (30-min: Jan 2024 → Jun 2026 · 15-min: Aug 2025 → Jun 2026)

Tier	Net P&L	Win Rate	Profit Factor	Max DD	Profitable Months
🛡️ TITAN · PRIME · 30M · 9–12 ET (prop firm pick)	+$200,489	70.8%	2.67	-1.73%	30 / 30 ✓
⚖️ TITAN · EXTENDED · 30M · 9 AM–1 PM ET	+$228,540	70.2%	2.46	-1.71%	30 / 30 ✓
🎯 TITAN · GOLDEN · 30M · 10 AM–1 PM ET	+$124,583	70.6%	2.06	-1.79%	29 / 30
🚀 RAPTOR · PRIME · 15M · 9–12 ET	+$75,990	69.2%	1.88	-1.93%	11 / 11 ✓
⚡ RAPTOR · EXTENDED · 15M · 9 AM–1 PM ET (recommended)	+$89,870	68.8%	1.78	-1.78%	11 / 11 ✓
🏆 RAPTOR · GOLDEN · 15M · 10 AM–1 PM ET (live-validated)	+$48,840	69.7%	1.59	-2.32%	10 / 11
🥇 GOLD · 30M · GLOBEX session (around-the-clock) (Elite-exclusive · DEEP · last 365 days · not yet live-validated)	+$88,620	67.4%	1.28	-2.84%	13 / 13 ✓

Backtest periods (TradingView data depth): 30-min modes Jan 2024 → Jun 2026 (~30 months) · 15-min modes Aug 2025 → Jun 2026 (~11 months). MNQ, ATR risk-based sizing (cap 2), $100K account, Bar Magnifier ON. Net is period-dependent — don't compare 30-min vs 15-min net directly.

Hypothetical backtested results — 30-min modes Jan 2024 → Jun 2026 (~30 months), 15-min modes Aug 2025 → Jun 2026 (~11 months); Gold backtested separately on the last 365 days (DEEP detalization). RAPTOR · GOLDEN figures above are backtest; the same mode is live-broker validated separately at PF 3.13 / 88.7% WR over 62 trades in its best week (May 11–15) on our personal NinjaTrader account (see below). Past performance does not guarantee future results. Apply a 20–30% haircut when projecting real-world performance. Gold is backtest only — not yet live-validated. Demo for 7+ days before going live with real money.

Live Broker Validation (RAPTOR · GOLDEN Tier · Real NinjaTrader Account)

The RAPTOR · GOLDEN tier is also live-broker validated on our personal NinjaTrader account — real money, real slippage, real exchange fees. 62 trades in the 10am–1pm window · Live PF 3.13 · 88.7% WR · $2,582 across 5 days (May 11–15) · backtest PF 1.59 (2× better live). Live beats backtest 2× — empirically rare in this space. Most algorithm sellers exploit TradingView's bar magnifier inflation (which can inflate tight-stop strategies up to 5×) to publish flashy backtests that crater in live. Falcon AI was tuned around what survives a real broker (wider stops, cleaner sessions) — that's why the live broker number is HIGHER than the backtest, not lower.

We don't sell backtests. We sell what we trade. See /transparency for the full live vs backtest comparison + the exact broker statements (NinjaTrader live + Topstep daily screenshots).

04Limitations

Backtesting provides useful directional insight into signal methodology but has significant inherent limitations that all subscribers must understand before placing any live trades based on Falcon AI signals.

Slippage is modeled, but real markets vary — Backtests apply 1 tick of slippage per fill. In live markets, particularly around news events or in thin pre-market/overnight sessions, actual fills can still slip further than one tick.
Commissions are modeled at a typical rate — Backtests deduct $1.50 per contract per side. Your broker’s actual commissions, plus exchange and NFA fees, may be higher or structured differently than the modeled rate.
Look-ahead bias risk — Despite rigorous controls, Pine Script-based backtesting environments carry a residual risk of unintentional look-ahead in complex multi-timeframe scripts. Results should be treated as optimistic estimates.
Survivorship bias — The instruments tested remain highly liquid today. Contracts or markets that experienced structural changes or delisting are not represented in the data set.
No execution psychology — A backtest assumes every signal is acted upon exactly. In live trading, traders frequently miss signals, enter late, exit early, or skip trades — all of which affect actual results.
Changing market conditions — The SMC patterns and AI confluence thresholds used in the backtest reflect historical effectiveness. Future market regimes, regulatory changes, or shifts in institutional order flow behavior may reduce the signal engine's effectiveness.

Hypothetical Results Disclaimer

All backtesting results presented by Falcon AI are hypothetical in nature and do not represent actual trading performance. Hypothetical results have many inherent limitations and no representation is made that any account will or is likely to achieve profits or losses similar to those shown. Past performance is not indicative of future results.