FM Foundry by SiriusAIReach out to us

Foundation Models are revolutionizing all customer decisions for Financial Services. Creating exponential P&L benefits in one shot

SiriusAI builds custom foundation model on your own transaction and interaction data, inside your environment in 3 months. Acquisition, collections, cross sell, fraud and credit all build on it.

FM Foundry by SiriusAIbyLearn How Foundation Models Works
RevolutMarket implementation

Foundational sequence model across user journeys

+65%
fraud detection accuracy

-40%false positive declines

FM Foundry by SiriusAIImplementation

Credit Risk foundation model

3.5%
higher customer approval rates

80%less feature engineering effort

AffirmMarket implementation

Multi-task foundation model for consumer credit risk

+3.4%
incremental approval rate

-12%30-day delinquency

FM Foundry by SiriusAIImplementation

Transformer based foundation model

24%
collections performance improvement

21%better collections performance than existing models

FM Foundry by SiriusAIImplementation

Transformer-based sequential recommendation system

40%
lift in customer engagement, on the same model

$70Mnannual business value generation

Capital OneMarket implementation

Transaction graph transformer, commercial and retail

+26%
early stress detection lift

3.2xfaster model onboarding

StripeMarket implementation

Radar foundation model on global network events

59→97%
fraud detection for card-testing

3.8%–7%increase in authorization acceptance rates

Force Multiplier in decision systems:One AI model trained on all your rich internal data,which every function or domain can adopt for its own decisions

Traditional Decision Systems for past 20 years

One machine learning model per task

Structured Data tables
Machine Learning Model A
Credit Scoring
Structured Data tables
Machine Learning Model B
Fraud Detection
Structured Data tables
Machine Learning Model C
Collections
Structured Data tables
Machine Learning Model D
Marketing

Decisioning done with aggregated summaries; losing granularity of customers data, leading to stagnated model performance

Foundation Model: new age AI decisioning brain

ONE model, adapted for many tasks and uses

  • Transactions & paymentsSwipes, merchants, amounts
  • Accounts & balancesInflows, balances, timing
  • App & service activityLogins, sessions, journeys
  • Bureau & external dataBureau and market signals

Trained once on billions of events without losing any granularity

Foundation Model
Unique Embeddings Profile of every customer
  • Credit modelCredit & lending decisions
  • Fraud modelFraud & financial crime decisions
  • Collections modelCollections & recovery decisions
Billions of events, in sequenceFull customer context in every decision modelNo details lost to aggregation

For 20 years, traditional decision systems have missedthe richness of sequence and timing in your data.

Foundation models capture every detail behind every decision.

What a foundation model sees

Every event over the same 90 days, in order. The order and the spacing are the signal.

Month 1Month 2Month 3
Money in
Money out
App and digital
Service contact
Credit and risk
1
2
3
4
1Day 35

Salary 3 days late, then 7 days late the next month.

2Days 56–63

Balance transfer, savings order cancelled, a credit search elsewhere.

3Day 75 on

Logins go from weekly to daily, mostly late-night balance checks.

4Day 88

A direct debit bounces: the first thing the scorecard sees.

Behaviour profile: early financial stressHold the increase and offer early supportWarning signs caught from day 35, 53 days earlier

Foundation Model saves 70% of the technology cost and time.Traditional models are built from the ground up, every time.

Traditional models

0 wks
of feature work
Model 1Model 2Model 3
Features for Use Case 1
Features for Use Case 2
Features for Use Case 3

Foundation model

0 wks
once
Foundation model
Use Case 1
Use Case 2
Use Case 3
Time saved
  • Data, training and validation
  • Feature engineering
  • Events prepared once
  • Foundation model training
  • Use case

FM Foundry has proven impact across multiple clients implementations.

Custom foundation models, trained on each client's own data inside its environment, now run live decisions at leading payments and banking firms.

Recent Implementation Live
  • Foundation model

    Replaced 20-year-old decision technology in one step

  • Credit riskLive

    20% lift in performance, 4% more customers approved

  • CollectionsLive

    +25% roll-rate transition performance, lower losses

  • Cross-sellLive

    40% lift in customer engagement, on the same model

Every new use case70% less build time

10B+ unique data points trained on

Trained on 100M+ customer records

Every new use case80% less data prep

Solution to build your custom foundation model in 12 weeks

FM FoundrybySiriusAI

See it in action
01Data & Behavior
Readiness ProfilerEvent Ontology
02Foundation Model Factory
Tokenization & SequenceArchitecture WorkbenchModel Training Engine
03Proof & Economics
Benchmark & AblationModel Economics
04Intelligence & Inferencing
Embeddings & Task HeadsServing / Monitoring
9 modules in 4 layers
FM Toolkit demoVideo placeholder
  1. Data discovery & readinessWk 1–2
  2. Event sequencing & tokenizationWk 3–4
  3. Foundation model, trained from the ground upWk 5–8
    Wk 8Your custom foundation model
  4. Decision models on FM embeddingsWk 9–12
    Wk 121 use cases ready for live evaluation

Frequently asked questions

Within the first quarter, compared with the models you run today.

An LLM learns language. A transaction FM learns behaviour from your own events and gives every use case a rich profile of each customer.

No. It plugs into your data platform and decision systems, and can start by strengthening the models you already run.

No. Training and scoring run inside your environment, on your credentials.

You do: the foundation model, every use case layer and the documentation.

Decisioning of tomorrow.
Available today.

Reach out to usMore about Sirius AI →
FM Foundry - Custom Foundation Models for Financial Services