Skip to main content
CyPredict v1 launching
CyPredict — XAUUSD Decision Engine

How it thinks · CyPredict

Transparent pipeline no magic

The signal engine is rule-based and auditable. The news engine's formula is spelled out below. We publish what we do because trust is the product.

Signal replay · Illustrative

Watch the engine fire BUY / SELL signals as price moves

The same decision loop the live dashboard runs, replayed on a fixed tape — candles print in, three setups fire, and cumulative P&L integrates across the window so you can see every entry, stop, and target land.

Cumulative P&L · live tickLive replay
By the CyPredict engine · illustrative decision replayZero repaint · audited

System pipeline

How the engine thinks

Twelve wires and the live tape feed one decision surface. Every stage is rule-based and auditable — from raw price to a delivered XAUUSD decision.

  1. 01Step 01

    Ingest

    Watching XAUUSD OHLC across 5m / 15m / 1h plus curated macro sources — Trading Economics calendar, Finnhub real-time wire, Benzinga commodities channel, Firecrawl-scraped Kitco / FXStreet pages, GNews aggregation. Sources toggle from /admin without a redeploy.

  2. 02Step 02

    Classify · Score

    Every news item is deduplicated (SimHash @ 64-bit, threshold 0.85), categorised across ten enums (inflation, fed, rates, yields, geopolitics, …), then scored 0–100 with a transparent admin-tunable formula. No black-box ML.

  3. 03Step 03

    Build context

    The context aggregator rolls high-impact items into macro bias, shock risk, suggested posture, and a countdown to the next major event. Refreshed every minute, cached 60s in Redis.

  4. 04Step 04

    Run signal engine

    Rule-based decision engine: liquidity sweep detection, session timing, momentum (ROC + EMA slope), volume confirmation, and macro alignment combine into a 0–100 confidence score. Trap-risk overlay catches break-without-retest and 2σ volatility spikes.

  5. 05Step 05

    Explain

    Every emitted signal ships with CY commentary (CyIntelligence, 2-3 sentences) grounded in the same inputs. You can verify the reasoning against the chart — no opaque oracle.

  6. 06Step 06

    Deliver

    Timing window (NOW · SOON · WAIT · AVOID), entry zone, stop zone, two targets. Plus a live countdown to setup expiry, and macro override that down-weights confidence when news is about to break.

Rule-based and auditable · No black box

The readout, decoded

Six numbers, one posture

Bias

Direction, structural

Long or short, read from structure and session flow — never from a single candle.

Confidence

0–100, transparent

How much confluence backs the read. Low scores are published too — that is the point.

Trap risk

Fake-outs, called early

Liquidity sweeps and stop-hunts flagged before entry, not explained after.

Timing

NOW / SOON / WAIT

A window, not a countdown. If the window closes, the setup is retired.

Levels

Entry · stop · target

Drawn from the candle the engine fired on. Nothing repainted.

CY commentary

Context per signal

One paragraph of macro context per setup, written by CyIntelligence.

Every rule is documented. Every signal is traceable. If we cannot explain it, we do not ship it.

Confidence formula · Documented

How confidence is composed

confidence = clamp(
    structure   * 0.30 +   // liquidity sweep / break of structure
    session     * 0.15 +   // Asia / London / NY bonus
    momentum    * 0.20 +   // ROC + EMA slope
    volume      * 0.15 +   // volume delta vs average (redistributed when feed has no volume)
    macro_align * 0.20,    // alignment with news context
    0, 100
)

Weights live in system_settings, adjustable from the admin panel without a redeploy. When the upstream candle feed has no volume data (XAUUSD spot is one of those), the 0.15 volume weight is redistributed across the remaining factors so the score still sums to 100. The macro-override layer can also force timing_window=WAIT and zero out the macro contribution when news.context.suggested_posture is wait or avoid_new_entries.