Skip to content

Churn & health score engine

ID MOD-040
System SD06
Repo bank-risk-platform
Build status Deployed
Deployed Yes
Last commit 54197c02fff0ca78a988e6140d31778e59f05b46

Logistic regression model producing churn probability and engagement health score per customer weekly. Feeds NBA engine and triggers proactive outreach.

Streamlit dashboard

MOD-040 ships a Streamlit page RISK_CUSTOMER.STREAMLIT_CHURN_DASHBOARD providing: - Churn risk distribution across the customer base - Model accuracy (AUC) and PSI from last validation run - Top 10 feature drivers of churn predictions (SHAP values) - High-churn segment deep-dive

Consumed by MOD-172 (Operations & Model Intelligence Dashboard) in the model performance section. Cross-schema SELECT on RISK_CUSTOMER.* published views required for OPERATIONS_ROLE.


Module dependencies

Depends on

Module Title Required? Contract Reason
MOD-042 CDC pipeline — Neon logical replication to S3 Iceberg Required Churn and health scoring models are computed in Snowflake on transaction and engagement data from the CDC pipeline.
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-039 Customer risk score model Required MOD-039 owns the RISK_CUSTOMER schema and its DCM project — MOD-040 must deploy into the same schema and cannot create DTs there until MOD-039's schema governance (grants, ownership) exists.
MOD-172 Operations & Model Intelligence Dashboard Required Operations & Model Intelligence Dashboard shows churn model accuracy and PSI metrics in its model performance page.

Required by

Module Title As Contract
MOD-077 Account dashboard & insight feed Optional enhancement
MOD-107 Next best product engine Hard dependency
MOD-172 Operations & Model Intelligence Dashboard Hard dependency

Policies satisfied

Policy Title Mode How
CON-001 Customer Fairness & Conduct Policy AUTO At-risk customers proactively identified and contacted — fair conduct met before customer disengages
CON-003 Vulnerable Customer Policy ALERT Financial stress signals in health score can trigger vulnerable customer flag — automated identification

Capabilities satisfied

Capability Title Mode How
CAP-063 Proactive financial insight engine AUTO Contributes churn and engagement signals to the insight engine so recommendations account for customer health indicators.

Part of SD06 — Snowflake Analytics & Risk Platform Compiled 2026-05-22 from source/entities/modules/MOD-040.yaml