Redis Real-Time Decisioning Demo | Loan Approval Process

Stage 1: The Architecture

Northstar Lending's Real-Time Decisioning Stack

Five tiers form a continuous loop: ingest, context, decide, act, learn. The decision is not just approve or decline. It is approve, step-up, conditionally route, or cross-sell the right lending path in the same session. Systems of record stay where they are. Redis becomes the operational context layer that makes the moment actionable.

Data Sources

Loan Origination System

Operational source

Core Banking Platform

Operational source

Credit Bureau APIs

Operational source

Document Repository

Operational source

Fraud / Identity Platform

Operational source

Kafka / Application Events

Operational source

Ingest Layer

Redis Data Integration (RDI)

CDC from repositories and operational databases with sub-second activation

Redis Feature Form + Streams

Feature serving and live event hydration from Kafka, Redis Streams, and industry APIs

Unified Context Layer

Redis RAM

Hot application state, real-time credit signals, active verification steps, and live policy flags

Redis Flex

Warm credit and behavioral history, document embeddings, prior application context, and bureau data

Feature Store

Risk score, fraud propensity, income stability, and product eligibility features

Redis Context Retriever

Assembles the Applicant 360 — credit state, account history, and policy context — and exposes it as structured MCP tools for the decision engine

Decision Engine

Eligibility Rules

Policy, compliance, and inventory constraints

NBA Ranker

Contextual ranking weighted by value, risk, and fit

Policy Arbitration

One action selected for the current moment

Output Channels (Act)

Loan Portal

Customer-facing activation surface

Underwriter Desktop

Customer-facing activation surface

Branch Tablet

Customer-facing activation surface

SMS / Email

Customer-facing activation surface

↺

Learn: Decision logs and outcomes stream back into model training, policy updates, and the Redis context tier.

Decision latency

11.6 ms

Manual review reduction

-37%

Approval yield lift

+14 pts

Stage 2: Trigger Event

Daniel Lee creates a decision moment

A borrower completes a digital loan application and waits for an approval path on the confirmation screen. Assemble credit, fraud, income, and policy context before the underwriting UI renders.

Live Trigger

Daniel Lee

Prime borrower | 742 FICO | payroll direct deposit | repeat applicant

LENDING

Eventapplication_submitted

Customer surfaceLoan portal

Decision objectiveApproval + product steering

Decision windowBefore the surface finishes rendering

Context requiredHistory + live signals + policy

Business stakes-37%

Why This Moment Matters

The decision is not just approve or decline. It is approve, step-up, conditionally route, or cross-sell the right lending path in the same session.

Without Redis: the application waits on siloed repositories and defaults to a generic next step.

With Redis: the decision surface opens with ranked, contextual action already staged for the moment.

Stage 3: Ingest

Industry repositories and streams flow into Redis

These are common repositories and streaming APIs for lending decisioning. They remain the systems of record. Redis activates the working set needed to decide now.

Redis Data Integration (RDI)Redis Feature Form

Source Systems → Redis

FICO

FICO / Experian APIs

Common repository or streaming source for fico context

→

ENCO

Encompass / LOS

Common repository or streaming source for encompass context

→

CORE

Core deposits ledger

Common repository or streaming source for core context

→

KAFK

Kafka / Redis Streams

Event streaming via Kafka or Redis Streams — no separate broker required with Redis Streams built-in

→

PAYR

Payroll and income verification APIs

Common repository or streaming source for payroll context

→

Ingest Pipeline Status

CDC modeReal-time

Streaming lag<100 ms

Feature parityTrain = serve

Custom sync code0 lines

Serving roleOperational context layer

Stage 4: Context Assembly

History and live state converge into one working view

Redis assembles profile history, applicant or account state, live intent, and policy constraints in one low-latency lookup path. What looked like a simple event in Stage 2 becomes a much richer decision moment here.

Redis RAMRedis FlexRedis Context Retriever

Historical Context

Customer value band34%

Tenure / relationship depthEstablished

Prior interaction patternKnown baseline available

Eligibility stateResolved in memory

Policy constraintsCurrent and active

Action historyFrequency caps enforced

Live Context

Current intentApproval + product steering

Streaming signal stateFresh for this session

Capacity / inventoryAvailable

Risk / complianceWithin active rules

Surface readinessLoan portal

Decision scopeInstant conditional approval

Key insight: Redis Context Retriever surfaces applicant credit state, account history, and policy constraints via MCP tools — the winning action becomes obvious only when historical context and live signals appear in the same response path.

Stage 5: Feature Serving

Online features hydrate the ranker in milliseconds

Redis Feature Form serves model-ready signals from Redis with train-serve parity. No fan-out calls to downstream systems during decisioning. No stale fallbacks.

Redis Feature FormRedis Feature Store

credit_score_band

Model or ranking signal pulled online at decision time.

prime0.3 ms

fraud_risk

Risk and policy factor used to gate the action.

low0.4 ms

income_stability

Real-time feature served from Redis with train-serve parity.

high0.5 ms

debt_to_income_ratio

Real-time feature served from Redis with train-serve parity.

34%0.6 ms

relationship_value_score

Model or ranking signal pulled online at decision time.

0.820.7 ms

verification_readiness

Eligibility and readiness signal.

ready0.8 ms

Feature Serving Performance

Features Hydrated

186

P99 Lookup Latency

<15ms

Train / Serve Parity

100%

Stage 6: Ranking

Candidate actions are ranked for this moment

Rules, policies, vector similarity, and business weighting combine to rank the best action now. The winner is selected because it fits the moment, not because it is the easiest generic fallback.

Redis SearchNBA RankerRules Engine

#1 Winner

PRIMARY ACTION

Instant conditional approval

Approve with payroll verification and auto-pay incentive

NBA score0.94

#2 Candidate

ALTERNATIVE

Manual review route

Lower risk, but adds friction and fallout

NBA score0.79

Suppressed

POLICY

Out-of-policy jumbo offer

Suppressed by debt-to-income and collateral rules

Suppressed0.24

Stage 7: Business Impact

The value of choosing the right action now

Fast decisions matter, but the real value is choosing the right action while the moment is still open. Redis improves both latency and outcome quality.

Decision Economics

Decision latency11.6 ms

Manual review reduction-37%

Approval yield lift+14 pts

The key insight: value compounds when the decision surface uses live operational context instead of generic fallback logic.

Moment Outcome

Generic

Siloed systems
lower relevance

→

Redis

Context-aware
higher impact

Stage 8: Outcome

Same surface. Different decision layer.

On the left is a generic or delayed path. On the right is the Redis-powered experience with ranked action already staged. Same customer moment. Different outcome.

Generic Experience

Daniel Lee

Lending workflow

What the system knows

Partial profile, delayed retrieval, and limited live context.

Action shown

Manual review route

Outcome risk

The action fits broadly, but not the full moment.

Lower

relevance

Higher

fallback use

Siloed

context

Redis-Powered Experience

Daniel Lee

Decision-ready profile

#1 Next Best Action

Instant conditional approval

Approve with payroll verification and auto-pay incentive

Why it wins

Combines history, live signals, business value, and active policy constraints in the same low-latency response.

Visible impact

Manual review reduction: -37%.

High

relevance

Low

fallback use

Ready

before render

Stage 9: The Architecture, Proven

Architecture first. Architecture last. Outcome in the middle.

The same five tiers you saw at the start now tie directly to a measurable decision outcome. Common repositories and streaming APIs stay in place. Redis remains the operational decisioning layer that makes the customer moment work.

Data Sources

Loan Origination System

Operational source

Core Banking Platform

Operational source

Credit Bureau APIs

Operational source

Document Repository

Operational source

Fraud / Identity Platform

Operational source

Kafka / Application Events

Operational source

Ingest Layer

RDI

CDC and activation from systems of record

Streams + Features

Live event hydration and model parity

Unified Context Layer

Redis RAM

Hot application state, real-time credit signals, active verification steps, and live policy flags

Redis Flex

Warm credit and behavioral history, document embeddings, prior application context, and bureau data

Feature Store

Risk score, fraud propensity, income stability, and product eligibility features

Redis Context Retriever

Assembles the Applicant 360 — credit state, account history, and policy context — and exposes it as structured MCP tools for the decision engine

Decision Engine

Rules

Eligibility, compliance, and policy

Ranker

Propensity, value, and fit

Arbitration

One action selected now

Output Channels

Loan Portal

Customer-facing activation surface

Underwriter Desktop

Customer-facing activation surface

Branch Tablet

Customer-facing activation surface

SMS / Email

Customer-facing activation surface

↺

Learn: Outcomes feed retraining, policy updates, and future decisions without changing the systems of record.

Decision latency

11.6 ms

Manual review reduction

-37%

Approval yield lift

+14 pts