Customer risk score model¶


ID	`MOD-039`
System	SD06
Repo	`bank-risk-platform`
Build status	Deployed
Deployed	Yes
Last commit	`9d80aab2956e9f4c952dbd7e8efe426167e0506f`

XGBoost model scoring each customer's AML/financial crime risk on a 0–100 composite scale. Real-time path (60-second event-driven via Snowflake Stream + Task) and daily batch path (15-minute Dynamic Table) feed a unified v_current_scores view, with full score history maintained in an append-only table.

MOD-039 is a publisher only — it does not write directly into KYC or AML Postgres databases. Consuming domains subscribe to the bank.risk-platform/customer_risk_score_updated EventBridge event and maintain their own mirror tables:

bank-kyc (MOD-010) — bank_kyc.party.risk_scores_mirror (see SD02 data model)
bank-aml (MOD-016/017) — bank_aml.aml.risk_scores_mirror (see SD03 data model)

The XGBoost model ships with synthetic training data at V1. It is replaced with production data once 6 months of MOD-016/017 outcome flags accumulate via CDC (MOD-042).

Streamlit dashboard¶

MOD-039 ships a Streamlit page RISK_CUSTOMER.STREAMLIT_RISK_SCORE_DASHBOARD providing: - Customer risk score distribution histogram across the portfolio - Score band breakdown (low / medium / high / very high) with counts and % of portfolio - PSI vs. prior month and drift alert status - Geographic and product-type breakdowns

Consumed by MOD-171 (Risk Intelligence Dashboard) in the risk metrics overview and RAF summary. Consumed by MOD-172 (Operations & Model Intelligence Dashboard) in the model performance section. Cross-schema SELECT on RISK_CUSTOMER.* published views required for RISK_INTELLIGENCE_ROLE and OPERATIONS_ROLE.

Module dependencies¶

Depends on¶

Module	Title	Required?	Contract	Reason
MOD-042	CDC pipeline — Neon logical replication to S3 Iceberg	Required	—	Customer risk score model is trained in Snowflake on transaction and behaviour history from the CDC pipeline.
MOD-010	CDD tier assignment engine	Required	`contract/dbt/`	CDD profile data is a required input feature for the customer risk scoring model.
MOD-104	AWS shared infrastructure bootstrap	Required	—	MOD-104 provisions the S3 Iceberg bucket (Snowflake external tables), KMS key, and bank-risk-platform EventBridge bus ARN. Required before this module can be deployed.
MOD-102	Snowflake account configuration & governance	Required	—	Snowflake account and governance provisioned by MOD-102 must exist before this module can read or write Snowflake.
MOD-171	Risk Intelligence Dashboard	Required	—	Risk Intelligence Dashboard includes customer risk score distribution in its risk metrics overview and RAF summary.
MOD-172	Operations & Model Intelligence Dashboard	Required	—	Operations & Model Intelligence Dashboard includes customer risk model performance metrics in its model performance page.

Required by¶

Module	Title	As	Contract
MOD-017	ML behavioural scoring model	Optional enhancement	—
MOD-040	Churn & health score engine	Hard dependency	—
MOD-077	Account dashboard & insight feed	Optional enhancement	—
MOD-150	Risk management platform	Hard dependency	—
MOD-153	Customer acceptance engine	Optional enhancement	—
MOD-171	Risk Intelligence Dashboard	Hard dependency	—
MOD-172	Operations & Model Intelligence Dashboard	Hard dependency	—

Policies satisfied¶

Policy	Title	Mode	How
AML-002	Customer Due Diligence (CDD) Policy	`AUTO`	CDD tier informed by live customer risk score — not a static assessment at onboarding
AML-005	Transaction Monitoring Policy	`AUTO`	High risk score customers subject to enhanced monitoring automatically — no manual watchlist
DT-005	Model Risk Management Policy	`LOG`	Risk score model in model inventory — validated against AML outcomes quarterly

Capabilities satisfied¶

Capability	Title	Mode	How
CAP-063	Proactive financial insight engine	`AUTO`	Generates personalised financial insights from the customer's transaction history and delivers them via the app.
CAP-067	Idle cash detection	`AUTO`	Detects when savings balances are idle and surfaces a prompt to move funds into a higher-interest product.
CAP-012	Merchant name enrichment & logo	`AUTO`	Enriches raw merchant names from transaction data with clean display names and merchant logos using a merchant intelligence database.
CAP-013	Spend categorisation (auto + manual)	`AUTO`	Automatically classifies each transaction into a spend category (dining, transport, groceries, etc.) using the ML categorisation model; customers can override the assigned category.
CAP-055	KiwiSaver contribution visibility (NZ)	`AUTO`	Retrieves and displays KiwiSaver balance, contribution rate, and projected balance at retirement from the customer's KiwiSaver provider API — NZ customers only.

Part of SD06 — Snowflake Analytics & Risk Platform Compiled 2026-05-22 from source/entities/modules/MOD-039.yaml