Skip to content

Add Gateway section to fraud detection quickstart #3139

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sfc-gh-cnantasenamat wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Add Gateway section to fraud detection quickstart #3139

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
66512fe
Add Gateway A/B testing section to fraud detection quickstart
sfc-gh-cnantasenamat Apr 5, 2026
8f4b339
Fix service and model version numbering (V1/V2 instead of V2/V3)
sfc-gh-cnantasenamat Apr 20, 2026
d012a8e
Merge branch 'master' into fraud-detection-gateway-section
sfc-gh-cnantasenamat May 21, 2026
b7812dc
Merge branch 'master' into fraud-detection-gateway-section
sfc-gh-cnantasenamat May 22, 2026
d3cd2b4
Merge branch 'master' into fraud-detection-gateway-section
sfc-gh-cnantasenamat May 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
144 changes: 138 additions & 6 deletions .../build-real-time-fraud-detection-model-with-natural-language-in-snowflake-ml.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ language: en
environments: web
status: Published
feedback link: https://github.com/Snowflake-Labs/sfguides/issues
tags: Getting Started, Data Science, Machine Learning, Snowflake ML, Model Registry, SPCS, Fraud Detection, Cortex Code
tags: Getting Started, Data Science, Machine Learning, Snowflake ML, Model Registry, SPCS, Fraud Detection, Cortex Code, Gateway

# Build a Real-Time Fraud Detection Model with Natural Language in Snowflake ML
<!-- ------------------------ -->
Expand All @@ -19,13 +19,15 @@ tags: Getting Started, Data Science, Machine Learning, Snowflake ML, Model Regis
- Train an XGBoost machine learning model for fraud detection
- Deploy models for scalable inference with one-click deployment
- Create REST API endpoints for real-time online inference
- Set up A/B testing between model versions using Gateways for traffic splitting

### What You'll Build
A complete fraud detection pipeline featuring:
- Synthetic transaction dataset with realistic fraud patterns
- Trained XGBoost classification model
- Live REST API endpoint running on Snowpark Container Services (SPCS)
- Performance benchmarking with latency profiling
- Gateway for A/B testing across model versions with traffic splitting

![diagram](assets/diagram.png)

Expand Down Expand Up @@ -431,15 +433,15 @@ This single prompt triggers a complete deployment pipeline. First, the model is
```
MODEL REGISTRATION
============================================================
Registering model as ML.PROJECTS.FRAUD_XGBOOST_MODEL version V2...
Registering model as ML.PROJECTS.FRAUD_XGBOOST_MODEL version V1...

✓ SNOWFLAKE_SQL_EXECUTE Verify model V2 registration
✓ SNOWFLAKE_SQL_EXECUTE Verify model V1 registration
SQL Result (2 rows × 10 cols)
┌─────┬───────────────┬──────────────┬───────────────────┐
│ # │ name │ version_name │ min_num_arguments │
├─────┼───────────────┼──────────────┼───────────────────┤
│ 1 │ PREDICT │ V2 │ 7 │
│ 2 │ PREDICT_PROBA │ V2 │ 7 │
│ 1 │ PREDICT │ V1 │ 7 │
│ 2 │ PREDICT_PROBA │ V1 │ 7 │
└─────┴───────────────┴──────────────┴───────────────────┘
```

Expand All @@ -451,7 +453,7 @@ Then deployed to SPCS (this can take a few minutes as it builds the container):
┌─────┬─────────────────────────┬─────────┬───────────────┬─────────────┐
│ # │ name │ status │ database_name │ schema_name │
├─────┼─────────────────────────┼─────────┼───────────────┼─────────────┤
│ 1 │ FRAUD_INFERENCE_SERVICE │ RUNNING │ ML │ PROJECTS │
│ 1 │ FRAUD_INFERENCE_SERVICE_V1 │ RUNNING │ ML │ PROJECTS │
│ 2 │ MODEL_BUILD_4A237CD4 │ DONE │ ML │ PROJECTS │
└─────┴─────────────────────────┴─────────┴───────────────┴─────────────┘

Expand Down Expand Up @@ -562,6 +564,133 @@ It also breaks down the predictions by risk tier so you can verify the model beh
• With connection pooling, throughput reaches ~15.7 req/s on a single thread. Parallel requests would scale linearly.
```

<!-- ------------------------ -->
## A/B Test with Gateways

In production, you rarely swap a model overnight. Instead, you route a fraction of live traffic to the new version and compare results before committing. [SPCS Gateways](https://docs.snowflake.com/en/developer-guide/snowpark-container-services/gateway) make this simple: a single stable hostname splits ingress requests across multiple service endpoints by percentage, so you can A/B test model versions without changing any client URLs.

In this step we will deploy an improved V2 model as a second SPCS service, create a gateway that sends 80% of traffic to the proven V1 service and 20% to V2, then verify the split. Once the new version proves itself, we shift the gateway to 100% V2 with a single `ALTER GATEWAY` statement.

### Prompt

```
Train an improved V2 fraud model (try a lower learning rate and more
estimators), log it to the Model Registry, deploy it as a second SPCS service
called FRAUD_INFERENCE_SERVICE_V2, then create a Gateway called
FRAUD_AB_GATEWAY that sends 80% of traffic to the original
FRAUD_INFERENCE_SERVICE_V1 and 20% to the new V2 service. Test the gateway
endpoint.
```

### What Gets Generated

Cortex Code trains the updated model, registers it, and deploys a second service:

```
MODEL REGISTRATION
============================================================
Registering model as ML.PROJECTS.FRAUD_XGBOOST_MODEL version V2...
learning_rate: 0.05 (was 0.1)
n_estimators: 500 (was 200)

✓ SNOWFLAKE_SQL_EXECUTE Verify model V2 registration
SQL Result (2 rows × 10 cols)
┌─────┬───────────────┬──────────────┬───────────────────┐
│ # │ name │ version_name │ min_num_arguments │
├─────┼───────────────┼──────────────┼───────────────────┤
│ 1 │ PREDICT │ V2 │ 7 │
│ 2 │ PREDICT_PROBA │ V2 │ 7 │
└─────┴───────────────┴──────────────┴───────────────────┘
```

Once the V2 service is running alongside the original:

```
✓ SNOWFLAKE_SQL_EXECUTE Check running services
SQL Result (2 rows × 4 cols)
┌─────┬────────────────────────────────┬─────────┬─────────────┐
│ # │ name │ status │ schema_name │
├─────┼────────────────────────────────┼─────────┼─────────────┤
│ 1 │ FRAUD_INFERENCE_SERVICE_V1 │ RUNNING │ PROJECTS │
│ 2 │ FRAUD_INFERENCE_SERVICE_V2 │ RUNNING │ PROJECTS │
└─────┴────────────────────────────────┴─────────┴─────────────┘
```

Next, the gateway is created with an 80/20 traffic split:

```
✓ SNOWFLAKE_SQL_EXECUTE Create A/B testing gateway
CREATE OR REPLACE GATEWAY ML.PROJECTS.FRAUD_AB_GATEWAY
FROM SPECIFICATION $$
spec:
type: traffic_split
split_type: custom
targets:
- type: endpoint
value: ML.PROJECTS.FRAUD_INFERENCE_SERVICE_V1!inference
weight: 80
- type: endpoint
value: ML.PROJECTS.FRAUD_INFERENCE_SERVICE_V2!inference
weight: 20
$$;

SQL Result (1 rows × 1 cols)
┌─────┬──────────────────────────────────────────────┐
│ # │ status │
├─────┼──────────────────────────────────────────────┤
│ 1 │ FRAUD_AB_GATEWAY successfully created. │
└─────┴──────────────────────────────────────────────┘
```

Cortex Code retrieves the stable gateway URL:

```
✓ SNOWFLAKE_SQL_EXECUTE Get gateway endpoint
DESC GATEWAY ML.PROJECTS.FRAUD_AB_GATEWAY
->> SELECT "name", "ingress_url" FROM $1;

SQL Result (1 rows × 2 cols)
┌─────┬──────────────────┬─────────────────────────────────────────────────┐
│ # │ name │ ingress_url │
├─────┼──────────────────┼─────────────────────────────────────────────────┤
│ 1 │ FRAUD_AB_GATEWAY │ ab-gw-ml-proj-aws-us-west-2.snowflakecomputing.app │
└─────┴──────────────────┴─────────────────────────────────────────────────┘
```

It then sends 100 test requests through the gateway and confirms the split:

```
GATEWAY A/B TEST RESULTS
============================================================
Endpoint: https://ab-gw-ml-proj-aws-us-west-2.snowflakecomputing.app/predict-proba
Total requests: 100 | Errors: 0

Traffic Split Observed
┌──────────────────────────────────┬──────────┬──────────┐
│ Service │ Expected │ Observed │
├──────────────────────────────────┼──────────┼──────────┤
│ FRAUD_INFERENCE_SERVICE_V1 │ 80% │ 78% │
├──────────────────────────────────┼──────────┼──────────┤
│ FRAUD_INFERENCE_SERVICE_V2 │ 20% │ 22% │
└──────────────────────────────────┴──────────┴──────────┘

Prediction Agreement: 96% (both versions agree on fraud/legit label)
V2-only catches: 2 additional fraud cases flagged by V2 but missed by V1
```

### Shifting Traffic

Once you are confident in V2, shift all traffic to the new version:

```
Shift the FRAUD_AB_GATEWAY to send 100% of traffic to
FRAUD_INFERENCE_SERVICE_V2. Confirm the change took effect.
```

The gateway hostname stays the same, so no client changes are needed. You can also use this pattern for high availability by splitting traffic across services running on different compute pools.

> Note: Gateway routing automatically fails over to healthy endpoints. If one service becomes unavailable, traffic is redirected to the remaining endpoints proportionally. See the [gateway failover documentation](https://docs.snowflake.com/en/developer-guide/snowpark-container-services/gateway) for details.

<!-- ------------------------ -->
## Debug and Recover from Errors

Expand Down Expand Up @@ -663,6 +792,7 @@ Congratulations! You've successfully built a complete real-time fraud detection
- Train an XGBoost model optimized for imbalanced fraud detection
- Deploy models to SPCS with automatic containerization
- Create and test REST API endpoints for real-time inference
- Use Gateways to A/B test model versions with traffic splitting behind a stable URL

### Related Resources

Expand All @@ -676,3 +806,5 @@ Technical Documentation:
- [Cortex Code Documentation](https://docs.snowflake.com/en/user-guide/cortex-code/cortex-code) - Getting started with Cortex Code
- [Snowpark Container Services](https://docs.snowflake.com/en/developer-guide/snowpark-container-services/overview) - Deploy and manage containerized workloads
- [Snowflake Model Registry](https://docs.snowflake.com/en/developer-guide/snowflake-ml/model-registry/overview) - Register, version, and deploy ML models
- [SPCS Gateways](https://docs.snowflake.com/en/developer-guide/snowpark-container-services/gateway) - Route ingress traffic to multiple service endpoints
- [CREATE GATEWAY](https://docs.snowflake.com/en/sql-reference/sql/create-gateway) - SQL reference for creating and configuring gateways
Loading