Architect Handover Document (`ARCHITECT_HANDOVER.md`)

This document outlines the functional state of the Quant Terminal, the mathematical thresholds used by the HSL status triggers, and the structures of active data proxies.

1. Functional State of the Station

The Quant Terminal operates with 7 primary functional modules mounted in app/page.tsx:

Sandbox (activeTab === 'sandbox'): Solves Swamy-Arora random effects regressions.
Scanner (activeTab === 'scanner'): Visualizes live asset scanners.
Insider (activeTab === 'insider'): Tracks corporate insider trades.
Krypto Bayes (activeTab === 'crypto'): Implements Bayesian on-chain learning models, featuring a Walk-Forward Multi-Model Ensemble Radar (RF, XGB/GB, LR, SVM, MLP) and 15 independent Beta-Posterior trackers.
Ökonometrie (activeTab === 'events'): Conducts econometric event studies.
Eco Indicators (activeTab === 'macro'): Monitors 21 FRED macroeconomic and credit indicators.
AI Special Silo (activeTab === 'tech'): Tracks the tech CapEx overinvestment cycle.

All endpoints support a 60-minute in-memory caching TTL.

2. Core Mathematical Thresholds & Status Triggers

Indicators in the cockpit cards use HSL-tailored status lights (Emerald-Green, Amber, Flashing Neon Rose-Red).

Macroeconomics Silo (Module 6)

Card 1 (Inflation & Consumer):
- RED: CPI Inflation YoY \ge 3.0\%, Credit Card Delinquencies > 4.5\%, or Personal Savings Rate < 3.0\%.
- AMBER: CPI Inflation \ge 2.5\%, Credit Card Delinquencies > 3.5\%, or Personal Savings Rate < 4.0\%.
- GREEN: Normal operations.
Card 2 (Valuation & Liquidity):
- RED: Buffett Indicator Ratio > 150\%, or M2 money supply trend is DOWN.
- AMBER: Buffett Indicator Ratio > 130\%, or Reverse Repo (RRP) volume $< 400$B$.
- GREEN: Normal valuation limits.
Card 3 (Yield Curve & Credit):
- RED: 2S10S yield spread is inverted (< 0.0\%), or High-Yield Credit Spread > 5.0\%.
- AMBER: 2S10S spread < 0.1\%, or High-Yield Credit Spread > 4.0\%.
- GREEN: Positive term structure.

AI & Tech Silo (Module 7)

Card 1 (Monetization Gap):
- RED: Minimum Monetization Gap among constituents < -15\% (diminishing segment returns).
- AMBER: Minimum Monetization Gap < 0\% (CapEx growth outstripping segment revenue growth).
- GREEN: Positive monetization gap (revenue growing faster than capital expenditures).
Card 2 (Supply-Chain Velocity):
- RED: Velocity Index < 1.8x, or velocity trend is DOWN (buyers reducing forward commitments).
- AMBER: Velocity Index < 3.0x (buyer commitments softening relative to supplier inventory).
- GREEN: Normal supply speeds (\ge 3.0x).
Card 3 (Infrastructure Leverage):
- RED: Maximum CapEx-to-Depreciation Ratio > 4.0x, or maximum Debt-to-Equity Ratio > 1.2 (highly leveraged node expansion).
- AMBER: Maximum CapEx-to-Depreciation > 2.5x, or maximum Debt-to-Equity > 0.8.
- GREEN: Asset expansion supported by low-leverage ratios.

3. Active Data Proxy Models

AI Special Silo API Response Schema (`/api/tech/ai`)

{
  "dates": ["Q3-24", "Q4-24", "Q1-25", "Q2-25", "Q3-25", "Q4-25", "Q1-26", "Q2-26"],
  "liveDataAvailable": false,
  "timestamp": 1781274890000,
  "metrics": {
    "monetizationGap": {
      "name": "ROI-to-CapEx & Monetization Gap",
      "tickers": {
        "NVDA": {
          "current": -5.3,
          "previous": -4.2,
          "trend": "DOWN",
          "segmentRevenueGrowth": 3.1,
          "capexGrowth": 8.4,
          "roiToCapex": 2.6,
          "data": [
            { "quarter": "Q3-24", "monetizationGap": 0.0, "roiToCapex": 0.0, "segmentRevenueGrowth": 0.0, "capexGrowth": 0.0 }
          ]
        }
      }
    },
    "supplyChain": {
      "name": "Nvidia Supply-Chain Velocity Index",
      "unit": "x",
      "currentVelocity": 2.2,
      "previousVelocity": 2.5,
      "currentTurnover": 5.7,
      "currentObligations": 18700,
      "trend": "DOWN",
      "data": [
        { "quarter": "Q3-24", "nvdaInvTurnover": 5.2, "aggregateObligations": 14500, "velocityIndex": 3.2 }
      ]
    },
    "infrastructure": {
      "name": "Tech Infrastructure Leverage & Cluster Expansion",
      "tickers": {
        "MSFT": {
          "currentDE": 0.3,
          "currentCapExDep": 3.9,
          "trendDE": "UP",
          "data": [
            { "quarter": "Q3-24", "de": 0.34, "capexDep": 3.2, "debt": 77800, "equity": 228900 }
          ]
        }
      }
    }
  }
}

Crypto Multi-Model Ensemble API Schema (`/api/crypto/ensemble`)

{
  "isShieldActive": true,
  "predictions": {
    "BTC": {
      "rf": { "T1": 0.62, "T5": 0.58, "T10": 0.54 },
      "gb": { "T1": 0.65, "T5": 0.61, "T10": 0.51 },
      "lr": { "T1": 0.58, "T5": 0.57, "T10": 0.55 },
      "svm": { "T1": 0.60, "T5": 0.59, "T10": 0.56 },
      "mlp": { "T1": 0.64, "T5": 0.60, "T10": 0.53 }
    },
    "ETH": {
      "rf": { "T1": 0.60, "T5": 0.59, "T10": 0.54 },
      "gb": { "T1": 0.66, "T5": 0.61, "T10": 0.48 },
      "lr": { "T1": 0.58, "T5": 0.55, "T10": 0.56 },
      "svm": { "T1": 0.59, "T5": 0.59, "T10": 0.56 },
      "mlp": { "T1": 0.64, "T5": 0.59, "T10": 0.55 }
    },
    "SOL": {
      "rf": { "T1": 0.65, "T5": 0.58, "T10": 0.52 },
      "gb": { "T1": 0.63, "T5": 0.63, "T10": 0.54 },
      "lr": { "T1": 0.59, "T5": 0.58, "T10": 0.54 },
      "svm": { "T1": 0.60, "T5": 0.62, "T10": 0.56 },
      "mlp": { "T1": 0.66, "T5": 0.60, "T10": 0.51 }
    }
  }
}

PEAD Drift Radar API Response Schema (`/api/scanner`)

{
  "results": [
    {
      "ticker": "NVDA",
      "name": "NVIDIA Corporation",
      "peadSector": "Technology",
      "announcementDate": "2026-05-20",
      "daysElapsed": 25,
      "epsActual": 6.12,
      "epsConsensus": 5.58,
      "surprisePercent": 9.68,
      "driftStatus": "Active Drift",
      "isLiveApi": true
    }
  ],
  "isShieldActive": false
}

4. Fallback Protection & Operational Transparency Levels

The workstation enforces zero silent caching or historical data ingestion:

PEAD Drift Radar: Uses a dynamic state flag isLivePeadApi to toggle status rendering.
- Green Badge (🟢 LIVE EPS FEED): FMP API endpoint responded with real-world quarterly reports (isLiveApi: true).
- Amber Badge (⚠️ ARCHIV-DATEN (API OFFLINE)): Live API timeout, failure, or developer shield fallback active (isLiveApi: false).
Crypto Bayes Module:
- Full-Width Scannability: Layout structured into 100%-width, centered grids containing the Walk-Forward Ensemble Radar and Active Learning Feedback Loop.
- Strict Calendar Time-Locks: Enforces an ironclad delta check against the fixed system date (2026-06-17) through isHorizonPending. Horizons (1 day, 5 days, 10 days) remaining within their lock duration strictly display countdowns and remain in a pending state, preventing look-ahead evaluations.
- Row Expulsion: Clicking "Hide Row" updates the forecast record with isHidden: true locally and saves it to LocalStorage. Hidden rows are filtered out from table rendering but remain intact for the metrics engine.
- Hit Ratio Counter: Formatted as Hit Ratio Counter: [True Count] True / [Total Resolved Count] Total using {tracker.alpha} True / {tracker.alpha + tracker.beta} Total.
- Countdown Formatter: Remaining seconds under pending targets are formatted to human-readable durations (e.g. Verbleibend: 1 Tag, 19 Std) using formatRemainingTime.
- Accordion Matrix: Each log row is expandable via Chevron toggle, displaying the individual model prediction direction and success/failure correctness status checkmarks upon resolution.
- Multi-Accuracy Tracking: Shows distinct columns for T+1 Acc, T+5 Acc, and T+10 Acc rather than a single aggregated metric.
- Global Performance Metrics Panel: Mounted below the feedback loop, presenting Horizon Efficiency (Section A) and Estimator Hit Distribution (Section B) dynamically evaluated from localStorage logs.
- Regime Status Indicator: Renders glassmorphic conditional badges in the header of the Walk-Forward Radar based on "activeRegime" in the JSON payload (1 for Calm, 2 for Turbulent, 3 for Churn).
Quant Python Pipeline (pipeline.py):
- Intermarket Sentiment Ingestion: Fetches daily close values for Nasdaq Composite (^IXIC), Gold Spot (GC=F), VIX (^VIX), and Crypto Fear & Greed (Alternative.me API). Incorporates automatic forward-fill (ffill()) and backward-fill (bfill()) to process data gaps.
- Feature selection gateway: Restricts features passed to the estimators to those selected by Boruta & PIMP filters, while explicitly prioritizing and bypassing pruning for all high-alpha metrics (v_supply, asopr, sth_sopr, lth_sopr, theta, squeeze_risk, d_liq, f_comp, z_f, z_f_squeeze_trigger, cvd_inst, cvd_ret, div_cvd, lambda_kyle).
- Dynamic Meta-Learner Calibrator: Replaces the static \theta_{\text{conf}} = 0.55 with a dynamic calibration threshold computed as the mean training correctness probability (np.mean(train_r_probs)) inside each model loop, successfully resolving the 50% entropy block.
- Defensive Class Array Check: Detects if the target classes array has a size smaller than 2, applying deterministic training probability fallbacks.

9.5 KiB Raw Permalink Blame History

Architect Handover Document (ARCHITECT_HANDOVER.md)