Skip to main content
UnicornBurnBETA
Evaluate a dealFeaturesMethodologyPricing
// sign inStart free →
Evaluate a dealFeaturesMethodologyPricing// sign inStart free trial →

// failure intelligence · how it works

The only system that matches a deal to documented failure patterns — with verified accuracy.

Matched against 5,032 documented autopsies, editorially curated. 85.9% Top-3 match accuracy (76.4% primary cause only) · the largest curated startup-failure dataset. It surfaces structural risks worth investigating — not a prediction of any one company's fate. CB Insights and PitchBook don't publish cause-match accuracy because they map outcomes, not structural precedent.

Evaluate a deal →Request access for funds
5,032
VERIFIED AUTOPSIES
editorially reviewed · 15 structured dimensions
85.9%
TOP-3 ACCURACY
primary or secondary cause · n=5,032
76.4%
TOP-3 PRIMARY CAUSE
primary cause only
$1.4T
CAPITAL DESTROYED
estimated · documented failures

// data quality

What "editorially reviewed" means.

Every case in the database passes a structured review before it is published. The criteria are the same regardless of sector, geography or funding size.

01
Documented shutdown

The company must have demonstrably ceased operations, been liquidated, declared bankruptcy, or been acquired under distress. Pivots and rebrands are excluded.

02
Attributable cause

The primary cause of failure must be identifiable from public documentation — founder post-mortems, regulatory filings, press coverage, court records, or investor statements. If the cause cannot be substantiated, it is left unassigned.

03
Reconstructible timeline

Key milestones — founding, peak, first warning signals, shutdown — must be reconstructible from at least two independent sources. Survival months are computed from these dates, not estimated.

04
Human field assignment

Analytical fields — collapse style, hype cycle, moat type, fatal mistake, archetype — are assigned by a human reviewer, not generated automatically. Each field is a considered judgment, not a classification label from a model.

Cases that do not meet all four criteria are either excluded entirely or published with a "unverified" flag. The verified / unverified split is reflected in the precision metrics above — backtesting is always run on verified cases only.

// precision metrics

Model accuracy evaluation.

5-fold stratified cross-validation on the full editorial corpus. Every verified case is evaluated exactly once. n=5,032. Backtesting runs on verified editorial cases only.

MetricAccuracynCI
Top-3 (primary or secondary cause)85.9%5,032±1.2pp
Top-3 (primary cause only)76.4%5,032±1.2pp
VersionTop-3DatasetNote
V260.0%~1,500Baseline
V580.4%5,471Fatal mistake signal added
V661.9%16,112Dataset ×3 — retraining drop
V986.1%†17,044Multi-label metric only†
V12 (current)76.4% / 85.9%*5,032NB ensemble (α=0.8) + v8 retrieval

* V12: 76.4% primary cause only / 85.9% primary or secondary cause. 5-fold stratified cross-validation, n=5,032. NB ensemble (α=0.8) blended with v8 structural retrieval (α=0.2). Intermediate versions (V3, V4, V7, V8, V10, V11) not listed. † V9: multi-label metric only (primary or secondary cause). V6: dataset tripled (5k→16k) with external data; retraining from broader corpus temporarily reduced precision.

// model pipeline

Five steps in the risk analysis.

Each analysis runs the same deterministic pipeline. Every score is traceable to concrete signals.

Sector filter across 5,032 autopsies. If fewer than 15 candidates, expands to adjacent sectors with a penalty.
Deterministic
12 weighted signals: sector, moat, country, archetype, hype cycle, business model and more. 5 bonus functions.
12 signals
Adjusted by cause frequency in the real dataset. Prevents over-weighting common causes like 'competition'.
Calibrated on 5,032 cases
Two signals, blended: (1) base rates from verified cases — how often each cause appears in companies like yours (80% weight); (2) structural similarity — which exact past cases look most like your deal (20%). Traceable to specific signals, not a black box.
5,032 verified · 24h cache
Window of candidates with close scores. Final boost by founder archetype and matching secondary cause.
Top 10 · score ≥ 30

Exact parameters, bonus functions and bayesian adjustment values are proprietary and not published. The pipeline is auditable — every score is traceable to concrete signals.

// model signals

The six signals that most distinguish failures.

Approximate weights based on backtesting. A profile accepts up to 15 input fields; the model condenses them into 12 weighted scoring signals.

Sector20%

Primary pool filter. Highest discriminative power. Model anchor.

Country / Region14%

Exact or regional match. Captures regulatory and macroeconomic context.

Moat strength12%

The single field that most distinguishes failures in the data: +14.8% match accuracy when present.

Founder archetype10%

+9.3% — founder profile correlates strongly with collapse type in the matched data.

Hype cycle9%

Market cycle at founding. Neutralises temporal penalties.

Fatal mistake + semantics9%

New in V5. Exact and text-similarity matching of the primary fatal mistake. Includes unit-economics sub-classification (burn rate, CAC/LTV, margin compression).

Exact weights and internal model parameters are proprietary.

// reading the results

What the numbers actually mean.

The output is not a grade. Each number has a precise technical meaning that determines how to use it.

01
The score is not a failure probability

A score of 72/100 means the startup shares 72% of structural patterns with companies that failed in this pool, not that it has a 72% chance of failing. The model identifies resemblance, not destiny.

Structural similarity
02
Top-3 is more reliable than Top-1

The model identifies the primary failure cause in the Top-3 in 76.4% of analyses (85.9% when secondary cause also counts). Collapse causes overlap — if the cause you suspect appears in the Top-3, the signal is strong.

n=5,032
03
How to read the matches

Score ≥ 65: strong match, review the autopsy in detail. Score 40–64: moderate, relevant patterns but structural differences exist. Score 30–39: weak, pool is small, treat with caution. Closer score = more weight on that collapse timeline.

Min threshold: 30

// common questions

Frequently asked questions.

The questions we get most from investors and analysts before they start using the platform.

We don't sell guarantees — we give you the tools to verify it yourself. Every case has a source you can check: a founder post-mortem, a regulatory filing, press coverage, court records. The entire editorial process is documented on this page. We publish the full backtesting history, regressions included — not just the versions that looked good. If something doesn't add up, you'll find it.
// auditable · verifiable sources
In 76.4% of analyses, the correct primary failure cause appears among the first three results. In 85.9% of cases, it's there when secondary causes count too. We validated this on 5,032 verified cases — every single one evaluated exactly once. We publish the full version history, including the releases where precision dropped. That's not marketing copy; it's the actual number.
76.4% primary · 85.9% Top-3 · n=5,032
Every case goes through four checks before entering the database: the shutdown must be documented, the cause must be traceable to public sources, the key milestones must be reconstructible from at least two independent records, and all analytical fields are assigned by a human reviewer — not auto-generated. No scrapers, no unverified aggregators. Backtesting always runs on verified editorial cases only.
5,032 verified cases · editorial review
The model weights structural similarity, not exact match. A company doesn't have to be identical to a case in the database for the pattern to be meaningful — a similar moat, a comparable founder profile, a matching market cycle all carry weight. If there aren't enough cases in your exact sector, the algorithm automatically expands to adjacent sectors and flags it explicitly. A score below 40 in a small pool is a weak signal, and the output tells you that.
Auto-expansion · minimum threshold: 30
No, and it's not built for that. What it does is surface structural patterns worth investigating — it doesn't decide. A high score means "this profile looks like companies that failed." What you do with that is your call. Think of it as a sharper starting point for due diligence, not a shortcut around it.
Signal · not verdict
New cases are added continuously. The model cache refreshes every 24 hours, so every analysis runs against the current dataset. When enough new data comes in to justify retraining, we release a new version — what you see on this page is always what's running in production right now.
24h cache · V12 current
Building this requires three things at once: thousands of structured, verified cases (years of editorial work), a rigorous backtesting framework, and the willingness to publish the numbers even when they show a regression. Most data providers don't invest in the editorial infrastructure. Those who have data don't build the model. We did both, and we publish the results.
Largest curated dataset · published precision
Two different standards. Top-1 means the model's first guess matches the actual primary failure cause exactly. Top-3 means the right answer is somewhere in the first three. We lead with Top-3 because startup failures are rarely one-thing — unit economics problems, market timing issues, and execution failures tend to overlap. In practice, analysts work with the full cause distribution, not a single slot. For context: a random baseline across 15+ cause categories would get under 10% Top-1 and under 25% Top-3.
Top-1 = exact first hit · Top-3 = correct cause in top 3

// GET STARTED

Does any startup in your portfolio follow these patterns?

1 free risk match, no card — in 30 seconds. The full platform (IC memos, deal scouting, portfolio signals) includes a 7-day trial.

Evaluate a deal free →Book a demoor compare plans

// PLATFORM

FeaturesEvaluate a dealMethodologyPricingAPI

// COMPANY

AboutChangelogSecurityContact

// EXPLORE

AutopsiesRankingsInvestorsShare your story
© 2026 UnicornBurn
PrivacyTermsData RightsAccessibility