Criterica Intelligence — 23,706 production models trained on 475M+ real court records
Regulated Outcomes Governance

Expected outcomes you can put in front of a regulator.

Criterica builds expected-outcome intelligence that institutional and regulated buyers can actually deploy, with model cards, validation, explainability, and documentation prepared for the compliance teams that have to approve it.

"The test of regulated intelligence is not whether the model is accurate in a demo. It is whether a compliance officer can read its documentation, understand its limits, and sign their name under the decision it informs. Governance is what makes a score deployable inside a regulated institution."

Validation.

Whether expected outcomes match realized ones.

We check three things. Do the probabilities mean what they say, so a 70 percent prediction is right about 70 percent of the time. Does the model hold up on real cases it never saw. And does it match outcomes that actually happened across the 475M+ real court record base. A model only joins the 23,706 in production once it clears that bar on real data.

Probabilities that mean it

A 70 percent prediction is built to be right about 70 percent of the time, checked across the full range.

Tested on the unseen

Measured on real cases withheld from training, never seen while the model was built.

Checked against reality

Scored against outcomes that actually happened, never against invented data.

The evidence

Promotion is earned. We hold back the models we cannot defend.

A model does not reach production because we built it. It reaches production because it survived testing against real outcomes. The fleet is a funnel, and most of what we build never enters it.

28,212
Models built
Every candidate, registered and versioned.
23,706
In production
Promoted only after testing against real outcomes.
4,353
Held as stubs
Awaiting licensed data we do not yet have. We will not ship a model without the data behind it.
6
In experimental review
Held back for results too perfect to be real, signs the model had seen the answer in advance, or too few real cases to trust.
2
Suspended
One because its own inputs already contained the answer. One that was a simulation tool, not a real predictor.
10
Failed validation
Did not clear the bar, and was not shipped.
Real records only. Zero synthetic data in production.
Every model is tested against real outcomes it was never shown.
A 70 percent prediction is built to be right about 70 percent of the time.

We would rather hold a model back than ship one we cannot stand behind. That discipline is the difference between a dashboard and a data-science institution.

Governance Framework
01
Model cards & transparency
Procurement, model risk, compliance review

Every production model carries a documented model card: intended use, training-data vintage and provenance, validation performance, known limits, and the jurisdiction-case-type scope it was built for. There are no black boxes in the fleet. If a model is deployed, its card is available to the compliance team that has to approve it. A score with no documented basis is not a product Criterica ships.

02
Validation framework
Model validators, quant risk, second-line review

Each model is checked three ways: do its probabilities mean what they say, does it hold up on real cases it never saw, and does it match outcomes that actually happened across our 475M+ real court record base. The question is never whether a model sounds confident. It is whether its predictions came true. Only models that clear that bar join the 23,706 in production.

03
Bias & fairness auditing
Fairness review, regulated-use compliance, legal

Outcome prediction adjacent to courts draws fairness scrutiny, and it should. Criterica audits for disparate performance across protected and proxy dimensions and treats fairness testing as a standing feature of the validation pipeline, not an afterthought bolted on before a deal. Where a model shows performance Criterica cannot defend, it does not promote it. The audit is documented so a reviewer can see what was tested and what was found.

04
Explainability
Decision-makers, underwriters, defensibility review

Every score is accompanied by the reasons behind it: the features that drove the prediction and the direction each one pushed. A decision-maker should never have to defend a number they cannot explain. Explainability is not a separate report you request — it travels with the score, so the person putting capital or a reserve behind it can articulate why.

05
Security & data governance
InfoSec, CISO review, vendor due diligence

Data handling, access controls, encryption, and tenant isolation are designed to support SOC 2 and ISO 27001 control objectives. Client data is segregated per tenant and access is scoped and logged. Criterica does not claim a certification it does not hold; instead, the controls and their documentation are built to satisfy the control objectives a security review measures against, and that documentation is available to counterparties under diligence.

06
Model risk management — banks
Bank model risk, validation, regulatory examiners

Documentation is packaged for institutions that operate under model risk management practices consistent with SR 11-7 style expectations: clear statements of model purpose and limitations, independent validation evidence, ongoing monitoring, and a documented development process. The objective is not to assert compliance on a buyer's behalf — it is to give a bank's model risk function the artifacts it needs to conduct its own review and approve deployment.

07
Model risk management — insurers
Insurer model governance, actuarial, NAIC review

For insurance buyers, documentation is prepared to align with NAIC model governance guidance: governance roles, model inventory, validation and testing evidence, and limits on use. As with the banking framework, Criterica supplies the documentation a carrier's governance function requires so procurement and compliance can evaluate and approve the model against their own standards, across 89 jurisdictions in the fleet.

A note on framework language. Criterica does not represent that it holds SOC 2 or ISO 27001 certification, and does not assert that any deployment is "compliant" with SR 11-7 or NAIC guidance on a buyer's behalf. Those determinations belong to the buyer's own auditors, model risk function, and regulators. Criterica's role is to prepare the documentation and controls so those teams can conduct their review against their own standards and reach their own conclusion.

Review our governance.
Bring your compliance team. We built the documentation for them.