Work in progress — RisCook is not yet live. You're previewing the product direction.
Model validation, methodology-first

Stop guessing which tests your model needs. Know.

RisCook reads a model's type, purpose, and inputs, then returns the specific statistical and ML challenger methodologies your validation team should run — with the rationale a regulator will ask for.

40+ model archetypes 120+ challenger methods mapped SR 11-7 aligned rationale
Work in progressWIP RisCook is in active development — the recipes above show the direction, not a finished library yet.
model_type: PD_LOGISTIC
Validation Recipe · 014
Probability of Default
Logistic Regression
CHALLENGE
  • Population Stability Index PSI
  • Kolmogorov–Smirnov discrimination KS
  • Vasicek-adjusted backtesting BT
  • Variance Inflation Factor check VIF
  • Benchmark challenger: gradient boosted trees GBM
rationale.pdf attached ✓
How it works

From model card to test plan, in three steps.

No black box. Every recommendation traces back to a documented reason your audit trail can show.

01

Describe the model

Tell RisCook the model's type, business purpose, inputs, and the segment it scores — or pull it straight from your model inventory.

02

Get the recipe

RisCook returns the statistical and ML challenger methods appropriate for that model class, ranked by relevance and regulatory expectation.

03

Review the rationale

Each test ships with the reasoning behind it, so your write-up explains why a test was chosen, not just that it was run.

Model library

A growing library of model archetypes.

Each archetype carries its own validated set of challenger methodologies, built from regulatory guidance and validation literature.

Credit Risk

PD / LGD / EAD models

Scorecards, logistic regression, survival models.

PSIKSVasicek BT
Market Risk

VaR & Expected Shortfall

Historical simulation, Monte Carlo, parametric.

KupiecChristoffersenBacktest
ML / AI

Gradient boosted & neural scorers

XGBoost, LightGBM, shallow neural nets.

SHAP stabilityPDP driftAdversarial
Capital & IFRS9

ECL / impairment models

Staging models, macro overlay sensitivity.

Scenario sens.Stage migration
Fraud

Anomaly & transaction scoring

Isolation forests, autoencoders, rules hybrids.

Precision@kDrift monitor
Pricing

Derivative valuation models

Black-Scholes variants, lattice, simulation.

Greeks stabilityP&L attribution
Governance

Built for the people who have to defend the test plan.

  • 1

    Rationale, not just output

    Every recommended test links to the guidance or literature that justifies it — ready to drop into your validation report.

  • 2

    Full audit trail

    Every recipe generated is versioned, timestamped, and tied to the model card that produced it.

  • 3

    Your team stays in control

    RisCook recommends. Your validators decide. Override any test, and the override itself is logged with a reason.

Audit log — model_id: PD_LOGISTIC_014
recipe_generated2026-06-19 09:41 UTC
methodology_basisSR 11-7 §IV.B
tests_recommended5
tests_overridden1 (logged)
validator_signoffconfirmed
Request access

Give your validation team a defensible test plan in minutes, not weeks.

RisCook is currently onboarding model risk teams at banks, insurers, and asset managers.