Methodology
1. Architecture Overview
ZARQ Crypto Risk Intelligence consists of two complementary models that serve different purposes and use different data.
These are not the same model with different names. They measure different things, use different data sources, and carry different weights. They work together in pair selection: Trust Score drives relative ranking, DtD filters distress risk. Together with the Structural Collapse filter, they form the basis for ZARQ's early warning system — which detected 113 out of 113 token deaths with 98% precision in out-of-sample testing.
2. Trust Score
Trust Score assesses the overall reliability and quality of crypto entities (tokens, exchanges, DeFi protocols) based on publicly available data. Every token is scored 0–100 across five pillars and mapped to a Moody's-style letter scale from Aaa to D.
Five Pillars
| Pillar | Weight | What It Measures |
|---|---|---|
| Security | 30% | Audits, hack history, contract risk, reserves, ATH recovery, multi-chain presence |
| Compliance | 25% | Regulatory status, social presence, categorization, supply transparency |
| Maintenance | 20% | GitHub activity, volume activity, development upkeep |
| Popularity | 15% | Market cap rank, volume, social following |
| Ecosystem | 10% | Multi-chain support, DeFi integration, category breadth |
Rating Scale
Trust Scores are mapped to a Moody's-style letter scale used throughout the platform:
| Rating Class | Moody's Analog | Description |
|---|---|---|
| IG_HIGH | Aaa–Aa3 | Highest quality, minimal risk |
| IG_MID | A1–A3 | High quality — best-performing class for pair alpha |
| IG_LOW | Baa1–Baa3 | Investment grade, adequate quality |
| HY_HIGH | Ba1–Ba3 | Speculative, elevated risk |
| HY_LOW | B1–B3 | High risk |
| DISTRESS | Caa–D | Substantial risk of default |
Entity-Specific Scoring
Trust Score has separate scoring functions for tokens, exchanges, and DeFi protocols. The pillars and weights are identical, but input variables are adapted. Tokens use market cap, ATH recovery, contract verification, and GitHub metrics. Exchanges use CoinGecko trust score, proof of reserves, and trading volume. DeFi protocols use TVL, audit status, hack history, and chain deployments.
Validation
Retrospective analysis shows consistent separation: collapsed exchanges averaged 5.0/100 (vs. 44.5 platform average), collapsed tokens averaged 30.9/100. All major 2022–2023 collapses scored below platform average.
3. Distance-to-Default (DtD)
Adapted from Merton's structural credit model used by credit agencies for bonds, DtD measures how many standard deviations a token is from critical failure. Scale 0–5, where 5 = fully healthy and 0 = imminent collapse risk. Below 2.0 is the danger zone. Below 1.0 is imminent risk.
Seven Signals
| # | Signal | Weight | What It Measures |
|---|---|---|---|
| S1 | Liquidity Depth | 10% | Turnover, volume trend, volume stability |
| S2 | Holder Concentration | 5% | Whale activity, Gini coefficient, activity distribution |
| S3 | Ecosystem Resilience | 30% | Drawdown, volatility, momentum, acceleration, streak |
| S4 | Fundamental Activity | 10% | Volume trend, panic detection, price/volume divergence |
| S5 | Contagion Exposure | 25% | BTC correlation, downside beta — strongest predictor |
| S6 | Structural Risk | 5% | Flash crash frequency, spread, token age |
| S7 | Relative Weakness | 15% | Token performance relative to BTC (7d/14d/30d) |
Override Rules
| Condition | Action |
|---|---|
| 1 signal < 0.5 | Cap DtD at 1.0 |
| 2+ signals < 1.5 | Cap DtD at 1.5 |
| 3+ signals < 2.0 | Cap DtD at 1.5 |
| Stablecoin with DtD < 2.0 | Floor at 2.0 |
Alert Levels
| Level | Threshold | Top 50 Threshold |
|---|---|---|
| SAFE | DtD ≥ 4.0 | DtD ≥ 4.0 |
| WATCH | DtD ≥ 3.0 | DtD ≥ 3.0 |
| WARNING | DtD ≥ 2.0 | DtD ≥ 1.5 |
| DISTRESS | DtD ≥ 1.0 | DtD ≥ 1.0 |
| CRITICAL | DtD < 1.0 | DtD < 1.0 |
DtD Trend Classification
| Trend | DtD Change (4 weeks) |
|---|---|
| FREEFALL | < −1.0 |
| FALLING | −1.0 to −0.5 |
| SLIDING | −0.5 to −0.2 |
| STABLE | −0.2 to +0.2 |
| IMPROVING | > +0.2 |
4. Structural Collapse & Stress Detection
ZARQ's primary early warning system. Rather than relying on ML crash prediction models, the structural weakness filter uses a rule-based approach that has been validated out-of-sample with exceptional results.
Four Weakness Signals
| Signal | Condition | What It Catches |
|---|---|---|
| Trust Below 40 | Composite trust score < 40/100 | Fundamental quality deterioration |
| Momentum Collapse | Signal-6 indicator < 2.5 | Deep structural risk signal |
| DtD Below 3.0 | Distance-to-Default approaching danger zone | Sustained distress below safety threshold |
| Trust Decaying | 15+ point decline over 3 months | Rapid quality deterioration |
Alert Levels
Structural weakness ≥ 2 triggers STRUCTURAL STRESS — fundamentals weakening, two weakness signals detected, requires monitoring. When a third signal activates, the token escalates to Structural Collapse.
Structural weakness ≥ 3 triggers STRUCTURAL COLLAPSE — this token is breaking apart. Historically, 98% of tokens with this profile lost more than half their value. Most never came back.
Out-of-Sample Validation
Period: January 2024 – February 2026. Universe: 207 tokens.
| Metric | Value |
|---|---|
| Deaths detected (>80% drawdown) | 113 / 113 (100% recall) |
| Precision at >50% crash | 98% (172/176) |
| Precision at >30% crash | 99.4% (175/176) |
| Genuine false positives (<30% drawdown) | 1 / 176 |
| Idiosyncratic deaths warned | 100% (98/98) |
| Median warning drawdown | −31% |
| Median additional loss avoided | 58% |
| Tokens never recovered (>80% DD) | 95% |
5. Crash Probability
90-day forward probability combining DtD trajectory, TVL divergence, contagion exposure, and historical default patterns. Calibrated on 393 crash cycles. Lookup: (trend, alert_level) → P(crash >30% within 90 days).
| Trend | WARNING | DISTRESS | WATCH | SAFE |
|---|---|---|---|---|
| FREEFALL | 43% | 34% | 28% | — |
| FALLING | 37% | 30% | 25% | — |
| SLIDING | 33% | 28% | 20% | — |
| STABLE | 33% | 30% | 18% | 3% |
| IMPROVING | 20% | 18% | 12% | 2% |
6. Portable Alpha Strategy
The Portable Alpha strategy combines Trust Score-based pair selection with DtD distress filtering and bear market detection. Conviction-ranked long/short pairs generated from rating spreads and DtD differentials within investment-grade tokens.
Architecture
1. Trust Score-based pair selection — long top-quartile, short bottom-quartile within the same rating class (IG_MID)
2. DtD-based distress filtering — do not short tokens with DtD < 1.5
3. Bear market detection — skip when BTC monthly return < −15%
4. Capital allocation — allocate between pairs portfolio and cash/BTC based on regime
Implementation
Universe of ~85 major tokens, excluding stablecoins. Rating class: IG_MID only (best-performing class for pair alpha). Top 5 pairs per month based on conviction score (40% spread + 60% DtD differential). Max 2 pairs per token. 90-day holding period. Return cap: ±100% per leg.
Three Portfolios
| Portfolio | Strategy | Bear Regime |
|---|---|---|
| Alpha Fund | Pure long/short, 5 pairs | 100% cash (bear skip) |
| Dynamic Fund | BTC core + L/S overlay | 10% BTC, 30% L/S, 60% cash |
| Conservative Fund | Lower risk budget | 5% BTC, 20% L/S, 75% cash |
Paper trading launched March 1, 2026 with SHA-256 hash-chained audit trail. Every signal logged before market open. No hindsight. No adjustments. Live tracking at /paper-trading. Backtest results and historical performance at /track-record.
7. API Reference
Every model output maps to an API endpoint with defined JSON schema. All endpoints available at zarq.ai/v1/crypto/. Free during beta — 1,000 calls/day, no API key required.
| Endpoint | Model | Latency |
|---|---|---|
GET /v1/crypto/rating/{id} | Trust Score | <200ms |
GET /v1/crypto/ndd/{id} | Distance-to-Default | <200ms |
GET /v1/crypto/ratings | Trust Score (bulk) | <500ms |
GET /v1/crypto/signals | Active warnings | <200ms |
GET /v1/crypto/safety/{id} | Aggregated pre-trade check | <100ms |
GET /v1/crypto/compare/{a}/{b} | Head-to-head comparison | <300ms |
GET /v1/crypto/distress-watch | DtD < 2.0 filter | <300ms |
Example: Safety Check
GET /v1/crypto/safety/bitcoin
{
"data": {
"token_id": "bitcoin",
"safe": true,
"risk_level": "LOW",
"trust_grade": "A2",
"dtd": 3.03,
"alert_level": "SAFE",
"crash_probability": 0.03,
"flags": []
},
"meta": { "version": "v1", "response_ms": 12 }
}8. Limitations
Data History
The crypto market has approximately 10 years of history compared to traditional finance's 100+. All statistical results should be interpreted with this constraint.
What The Models Do Not Capture
Hacks and technical exploits, regulatory surprises, insider fraud (FTX-type events), political events, key personnel departures, and smart contract bugs. These are inherently unpredictable from on-chain and market data alone.
Execution Costs
Pairs backtest does not include transaction costs. Estimated cost: 0.5% per trade (entry + exit), approximately 1% round-trip per pair.
Sample Sizes
Crash probability table is based on 393 crash cycles with per-cell counts not reported. Structural Collapse OOS validation covers 207 tokens over 26 months.
Concentration Risk
The Portable Alpha strategy runs 5 pairs per month from ~85 tokens. This represents high concentration in individual positions. Portfolio-level drawdown depends on allocation variant chosen.
ZARQ Methodology v1.1 · Canonical reference · All other documents that diverge from this specification are superseded.