Fair-Lending Bias-Simulation Appliance
FL-BSA
FL-BSA (Fair-Lending Bias-Simulation Appliance) is a self-hosted fair-outcomes evidence appliance for regulated credit decisions. It runs inside the customer-controlled environment and helps teams review credit-decision, affordability, pricing, underwriting, and policy-review workflows.
Each run packages a PDF report, metrics, manifests, and certificates for governance, model-risk, audit, and regulatory review.
FL-BSA is being prepared for a full public stable release. It is not yet published; request the buyer/procurement pack to confirm current availability.
FL-BSA highlights
Customer-hosted
Run inside your VPC, VM, or other customer-controlled environment.
Outcome simulation
Stress-test lending decision patterns on synthetic borrower cohorts instead of live production decision traffic.
Evidence packs
Generate reports, manifests, and certificates that support audit, model-risk, and regulatory review.
Automated creditworthiness evidence readiness
The revised EU Consumer Credit Directive rules are due to apply from 20 November 2026. Article 18 requires documented and maintained creditworthiness-assessment procedures; where an assessment involves automated processing of personal data, it also provides consumer-request rights to human intervention, an explanation, and review.
Scope one workflow
Define the decision, period, policy or model version, population, exclusions, and evidence question before selecting a measure.
Map the evidence gap
Record the available outcome measures, threshold rationale, governance owners, action criteria, and missing evidence.
Keep control of the data
Plan a customer-hosted evaluation without sending borrower, model, or protected-attribute data to a vendor SaaS environment.
Equilens supports evidence-readiness review and controlled-evaluation planning. It does not provide legal advice, certify compliance, validate a model, or make live lending decisions.
How it works
Four steps from source snapshot to evidence prepared for governance review.
Step 1: Snapshot the baseline
Point FL-BSA at a bounded, read-only snapshot of features and decisions (prepared CSV/Parquet or a warehouse pull) to establish the baseline for the run.
Step 2: Simulate two branches
Train two generative branches. Amplification asks: are we amplifying the unfairness already in our history? Intrinsic asks: would the model still discriminate if history were fairer? The gap between them is the audit object.
Step 3: Generate hash-linked evidence
Every run emits a tamper-evident evidence manifest (SHA-256) plus certificates that link source data, model settings, and outputs.
Step 4: Review findings and act
Use the review-oriented report findings to tune models or document Less Discriminatory Alternatives (LDAs).
In build: measurement on your own decisions. Today FL-BSA evidences fairness on simulated decision patterns learned from your historical data; it never executes your models. We are building a production-targeted measurement mode for unsigned aggregate fairness measurements over customer-authored decision or score columns. It is in active development and is not part of the current release.
Deployment
Choose the customer-hosted path that fits your procurement and infrastructure model.
AWS AMI-first
The intended AWS deployment path is AMI-first. Public AWS Marketplace access is not yet available; any pre-release AMI evaluation or private handoff requires separate approval.
Container
Deploy the container stack via docker-compose in your VPC, VM, or on-prem environment.
See Procurement & Deployment for deployment steps and prerequisites.
Release path
Public release and current access
Full public stable release is the product destination. It is not yet published; current conversations cover evidence readiness, procurement, pricing, and separately scoped optional evaluations.
Evidence-readiness assessment
About 5 business days. For teams that want a fast stop/go answer. You get a short findings memo on your workflow, schema, data boundary, and evidence gaps, with a recommendation. The recommended first step.
Evidence readiness sprint
About 2 weeks. For teams preparing a controlled evidence run. You get an evidence-gap memo, a draft evidence-pack acceptance checklist, and a scoped plan for the run.
Fair outcomes evidence sprint
6 to 10 weeks. One controlled, customer-hosted FL-BSA simulation, with traceable simulation outputs, an explicit limitations record, and a governance readout.
Teams still defining the workflow can start with the assessment. Teams with a bounded question and customer-controlled environment may separately scope an optional pre-release evaluation. Pricing is provided on request. Requesting the pack gets you a written reply with the buyer and procurement pack (evidence-bundle samples, control mapping, deployment and security materials, and a commercial overview); it commits you to nothing further.
Release and current access
- Release destination: Full public stable release; no publication date is stated here.
- Current requests: Buyer/procurement pack, evidence-readiness assessment, pricing, or a separately scoped optional evaluation.
- Commercial terms: Finalized for the available release and delivery path; any pre-release handoff requires separate approval.
Annual and volume licence structures are post-qualification options, not public cold-sell offers.
Optional pre-release evaluation
Evaluate FL-BSA before public release
We are preparing FL-BSA for a full public stable release. An organisation with a time-bound need may separately scope one controlled, customer-hosted evaluation before publication. That optional engagement is not the release programme, a release gate, or the destination for FL-BSA.
Step 1: Agree the question
Define one workflow, one evidence question, the approved input boundary, and the proceed, pause, or stop criteria.
Step 2: Run FL-BSA
Support one customer-hosted simulation run. Borrower, model, and protected-attribute data stay inside your environment.
Step 3: Review the result
Review the simulation report, metrics, manifest, assumptions, limitations, and a practical next-step recommendation.
What an optional evaluation includes
- A typical 6 to 10 week engagement around one regulated-credit workflow.
- An evaluation plan and runbook for the agreed scenario.
- One supported, customer-hosted FL-BSA simulation.
- Traceable simulation outputs and an explicit limitations record.
- A governance readout and proceed, pause, or stop recommendation.
Why this question matters now: EU AI Act Article 4a includes whether bias detection and correction can be achieved effectively with other data, including synthetic or anonymised data, among the conditions for its exceptional special-category-data route. An evaluation records what the simulation establishes and what it does not.
Governance evidence
Materials and controls designed to support security review, vendor due diligence, and regulatory dialogue. The EU AI Act high-risk rules for relevant creditworthiness and credit-score systems are now due to apply from 2 December 2027; these mappings can support evidence preparation. This is not legal advice.
FL-BSA is a simulation and evidence-packaging tool. It does not certify regulatory compliance or replace legal, compliance, or model-risk judgment.
Product scope
- Self-hosted appliance: AWS AMI-first or Docker deployment, subject to the available release path.
- Data boundary: No borrower, model, or protected-attribute data sent to vendor SaaS in self-hosted deployments.
- Fairness metrics: Adverse Impact Ratio (AIR), selection-rate gap, statistical parity, and equal opportunity/odds, per protected group and per branch.
- Evidence bundle: PDF report, evidence manifest (SHA-256), certificate appendix.
Controls & mapping
- Control mapping: FCA, EU AI Act, and ECOA touchpoints documented.
- Security posture: Hardened images, optional Prometheus metrics.
- Change management: Versioned releases.
Licensing & usage
- Usage terms: Finalized for the available release and delivery path.
- Marketplace access: Public AWS Marketplace access is not yet available; any supported pre-release access is coordinated separately.
- SLA and services: Custom SLA terms and professional services statements of work are executed separately.
Open-source components are catalogued at /legal/.
Documentation
Public materials for evaluation, plus licensed technical docs for implementation teams.
Whitepaper
Public demo whitepaper covering FL-BSA's regulated-credit evidence model. The intake ZIP is an unsigned, non-evidence-grade diagnostics bundle with aggregate synthetic-data and fairness inputs used for the public whitepaper build. See the whitepaper page for provenance and verification steps.
Example report
Pinned public demo report generated from the balanced scenario in the public GOLD run fixture. The ZIP is the supporting synthetic/demo GOLD run pack: balanced scenario artifacts, companion validation scenarios, row-level synthetic demo datasets, certificates, manifests, and evidence guides.
Evidence-readiness note
Five practical checks to make before testing one credit workflow for fair outcomes: decision scope, the evidence question, data boundaries, named owners, and action criteria.
Public demo release: v5.0.0-rc9-public-fix-2724455 (non-commercial prerelease). The downloads above are selected synthetic/demo assets from that public release; they are not customer output, legal advice, or proof of a public Marketplace launch.
Technical docs
Licensed customers receive technical documentation, API references, and integration guides through our secure portal.
FAQ
Does any customer data leave our environment?
No. FL-BSA is self-hosted; all compute happens in your VPC or VM. It does not exfiltrate model parameters, raw data, or SCPD to Equilens-controlled services. Optional AWS Marketplace usage metering is enabled only by configuration.
How long does a typical run take?
FL-BSA does not currently publish a validated exact-version native sizing baseline or customer SLA. Measure the exact delivered artifact on the target hardware; runtime depends on input shape, hardware, configuration, and enabled validation work.
Which regulatory frameworks are covered?
Evidence maps to ECOA/Reg B (US), EU AI Act, and FCA Consumer Duty. Certificate families include input validation, data profiling, hyperparameter tuning, model, generation process, synthetic quality/validation, and regulatory mapping.
How can FL-BSA be deployed?
FL-BSA is being prepared for a full public stable release, which is not yet published. The intended AWS path is AMI-first, and supported container/VM paths may be agreed separately. Public AWS Marketplace access is not yet available. The selected native v5 runtime is CPU-based and does not require a GPU.
What is included in the evidence bundle?
A PDF report, an evidence manifest (dataset hash, RNG seed, software version), and certificates. Artifacts are hash-linked for auditability and can be retrieved by Task ID.
Does FL-BSA test our actual production model?
Not in the current release. FL-BSA simulates decision patterns learned from your historical data; it does not load or execute your scorecard. We are building a production-targeted measurement mode for unsigned aggregate fairness measurements over customer-authored decision or score columns. It is not yet shipped.
Can we verify the evidence ourselves?
Yes. Evidence bundles are hash-linked (SHA-256) with a documented hashing spec shipped in the bundle. Where signatures are enabled, signed release manifests and vendor-authored evidence attestations can be verified against the published Equilens vendor trust root at /fl-bsa/trust-root.json. Direct-AMI/customer-local evidence may prove bundle consistency without proving vendor authorship. Verification is offline; no Equilens service is required.
Ready to scope readiness?
Request the buyer/procurement pack or a readiness conversation. It commits you to nothing beyond a written reply.