consumer-compliance-fair-lending

Reviews a population of adverse-action notices and the underlying credit decisions field-by-field — timing, content, specificity of cited reasons, traceability of those reasons back to the model and data, FCRA risk-score disclosure overlay, and disparate-impact red flags. Produces a Word memo for the consumer compliance second-line, the fair-lending lead, model risk, and counsel; flags non-compliant notices and AI / complex-model accuracy gaps; recommends action without finalizing any customer-facing change. Best for: - Consumer compliance second-line sampling adverse-action notices on a credit product, testing the population against the notification rule's timing and content obligations. - Model risk or fair-lending review of a credit decision model (including AI / ML scorecards) where adverse-action reasons are produced from feature contributions and the reviewer needs to test that the cited reasons are the principal reasons supported by the model. - Triage of consent-order remediation or supervisory finding around adverse-action notice deficiencies, where the population needs to be re-tested against the operative rule and the firm's remediation plan. Not the right tool when: - The question is the underwriting model's predictive performance or stability rather than its adverse-action reason generation (use `ai-governance-model-risk/validation-plan`). - The question is the pricing tier or ability-to-repay calculation rather than the notice content (use `compliance-testing` for product-level review). - The reviewer needs a final fair-lending determination or a credit decision; this skill surfaces red flags and recommends action for human decision, it does not approve, deny, or finalize.

Drafts a Section 1071 small-business lending data readiness assessment under the CFPB's revised final rule (May 1, 2026; effective June 30, 2026; compliance date January 1, 2028). Covers covered-financial-institution determination against the 1,000-covered-transactions threshold, covered-application and covered-credit-transaction scoping, the 12 CFR 1002.107 data-point inventory, applicant-demographic data-collection mechanics, the 12 CFR 1002.108 firewall design, recordkeeping under 12 CFR 1002.110, and reporting-and-filing readiness against the CFPB Filing Instructions Guide. Produces a readiness matrix per data point and a narrative gap memo for the named accountable executive. Best for: - Pre-compliance-date readiness check for a covered financial institution against the January 1, 2028 compliance date (now a single compliance date for all CFIs at or above the 1,000-transaction threshold; the prior tier-based schedule is superseded). - Threshold-determination work for a firm sitting at or near the 1,000 covered-credit-transactions floor in each of the two preceding calendar years. - Annual operating-state readiness refresh post-go-live, against the firm's first or subsequent submission cycle. - Vendor or loan-origination-system readiness assessment where 1071 data capture is vendor-supplied (the firm remains the covered financial institution; the vendor is the data-collection agent). Not the right tool when: - The question is HMDA / Reg C readiness (different rule, different population — refer the reviewer to a HMDA-specific routine). - The question is fair-lending testing on the originated 1071 portfolio (use `fair-lending-test-plan`; the 1071 dataset feeds fair-lending testing once it exists). - The question is the adverse-action notice for a small-business application (use `adverse-action-review`; Reg B 1002.9 applies). - The question is the firm's overall consumer compliance management system (use `risk-compliance-core` or `compliance-testing`).

Drafts a second-line UDAAP review memo for a product, feature, fee, disclosure or customer-experience flow, marketing motion, complaint pattern, or enforcement theme. Element-by-element analysis under Dodd-Frank §1031 (unfairness, deception, abusiveness) and §1036; consumer-harm hypothesis with population and magnitude; AI / algorithmic-discrimination tie-in where automated systems are in path; severity rating with rubric; conduct-risk implications; recommended remediation; cross-references to complaint, marketing, adverse-action, and fair-lending review. The memo surfaces UDAAP risk for human decision; it does not finalize a UDAAP determination, take down a live product, execute consumer redress, or issue any customer-facing action. Best for: - Pre-launch UDAAP review of a new product, feature, fee structure, or disclosure flow before a product or risk committee approves launch. - Targeted review after a complaint cluster (chain to `complaint-theme-analysis`), a regulator inquiry, or a peer enforcement action signals potential exposure on an analogous fact pattern in the firm's footprint. - Annual UDAAP risk-assessment refresh by product line, including overdraft, deposit-fee, card, mortgage-servicing, auto add-on, BNPL, instant-funding, and subscription-style fee mechanics. - Post-incident root-cause review where consumer harm has been alleged through complaints, social signals, employee escalations, or regulator engagement. - Annual review of an AI-driven personalization, pricing, or communication surface where the bureau's existing UDAAP authority reaches the algorithmic outcome. Not the right tool when: - The question is fair-lending under ECOA, the FHA, or §1071 (use `fair-lending-test-plan`; UDAAP and fair-lending overlap on themes such as steering and marketing distribution but are distinct legal frameworks). - The question is the adverse-action notice itself (use `adverse-action-review`; UDAAP touches AAN content where reasons obscure the actual decision logic, but the AAN-specific Reg B §1002.9 review lives next door). - The question is asset-level marketing-claim substantiation on a single creative or piece of copy (use `marketing-claim-review`; this skill addresses UDAAP at the product, fee, flow, or theme level, not the asset level). - The question is whether to file a complaint-theme escalation memo to the conduct or consumer-outcome committee (use `complaint-theme-analysis`; that skill produces the theme; this one tests a theme against the UDAAP elements). - A final UDAAP determination, a launch decision, a takedown, or a consumer-redress program is required. The memo is the input to the decision; the decision is reserved for the CCO, conduct-risk lead, head of consumer compliance, fair-lending committee, conduct committee, product committee, and counsel.

Aggregates and themes a population of consumer complaints (CFPB Complaint Database extracts, internal complaint-management records, app-store reviews, social signals, state-AG referrals, employee escalations) into named themes with severity, root-cause hypotheses, regulatory exposure mapping, and trended movements. Produces two artifacts: an Excel theme-aggregation matrix and a Word memo with the narrative analysis. Themes (not individual complaints) are the unit of analysis. The skill surfaces signal for the consumer compliance committee, the conduct committee, and the cross-skill chain into UDAAP, fair-lending, and adverse-action review; it does not finalise UDAAP determinations, fair-lending findings, or actions on individual complaints. Best for: - Quarterly or monthly complaint-themes pack to the consumer compliance committee, conduct committee, or risk committee. - Pre-exam preparation: re-running the firm's last 12 to 24 months of CFPB Complaint Database public data (and the firm-internal channels) against the current product set to triangulate likely examiner focus areas. - Triage after a regulator inquiry or a peer enforcement action on a specific product, to scope the population and trend at the firm. - Input to `udaap-risk-review` or `fair-lending-test-plan` when a theme suggests a specific product, fee, flow, or geographic concentration warrants element-by-element or finding-grade analysis. - Annual conduct-risk surveillance pack where complaint themes are the canonical signal feeding the conduct framework. Not the right tool when: - The question is one specific complaint disposition (use the firm's complaint case-management workflow). - The question is whether one marketing claim is misleading (use `marketing-claim-review`). - The question is statistical fair-lending testing on outcomes data (use `fair-lending-test-plan`; this skill flags, that skill finds). - The question is element-by-element UDAAP analysis on a specific product, fee, or flow (use `udaap-risk-review`; this skill themes the population, that skill tests the elements). - The question is the firm's overall CMS or compliance-program quality (use the broader compliance-testing or risk-compliance-core skills).

Drafts a fair-lending test plan covering scope, products, decision points (marketing, underwriting, pricing, steering, servicing, loss mitigation), planned test types (redlining, comparative file review, statistical regression on underwriting and pricing, marketing distribution, steering), demographic-proxy methodology, less-discriminatory-alternative search where AI or ML models drive credit decisions, data and evidence asks, controls hypothesis, owners, and committee approval gate. The plan is the operationalization of the annual fair-lending risk assessment and the artifact a fair-lending committee approves before any test is run. Best for: - Annual fair-lending risk-assessment refresh where the test plan is the operationalization of the assessment. - Pre-exam fair-lending readiness where a regulator has signaled focus on a specific product, MSA, or decision point. - Targeted plan after complaint themes (chain to `complaint-theme-analysis`) or adverse-action review (chain to `adverse-action-review`) surface a fair-lending red flag. - Bringing an AI or ML decisioning model into the fair-lending testing perimeter, including a less-discriminatory-alternative search. Not the right tool when: - The team needs the regression or comparative file review run, not the plan. This skill produces the plan; analytics runs the tests. - The question is the adverse-action notice itself (use `adverse-action-review`). - The question is Section 1071 small-business reporting readiness (use `section1071-readiness`). - A final fair-lending determination is required. The plan is reviewed and approved by counsel and the fair-lending committee; the determination follows the test, not the plan.