Predict Sanctioned Exchange Interaction
“Which addresses will send funds to sanctioned exchange addresses in the next 30 days?”
Book a demo and get a free trial of the full platform: data science agent, fine-tune capabilities, and forward-deployed engineer support.
By submitting, you accept the Terms and Privacy Policy.
Loved by data scientists, ML engineers & CXOs at
A real-world example
Which addresses will send funds to sanctioned exchange addresses in the next 30 days?
Garantex seized March 2025 after processing $96B. OFAC strict liability — intent doesn’t matter. If your users send funds to a sanctioned exchange, you face penalties regardless of knowledge. Penalties reach $10M per violation. Prediction is the only way to comply proactively.
How KumoRFM solves this
Graph-powered fraud intelligence
Kumo identifies pre-transaction patterns: addresses showing behavioral similarity to previous sanctioned-exchange depositors. The graph reveals that ADDR001 has 3-hop connections to Garantex deposit addresses and increasing transfer activity to intermediary wallets — signals that precede sanctioned exchange interaction.
From data to predictions
See the full pipeline in action
Connect your tables, write a PQL query, and get predictions with built-in explainability — all in minutes, not months.
Your data
The relational tables Kumo learns from
Addresses
| address_id | first_seen | entity_type | chain |
|---|---|---|---|
| ADDR001 | 2024-05-01 | individual | ETH |
| ADDR002 | 2024-07-15 | business | ETH |
On-Chain Transfers
| txn_hash | from_address | to_address | amount | timestamp |
|---|---|---|---|---|
| 0xa7... | ADDR001 | ADDR300 | 15.0 | 2025-01-08 |
| 0xb8... | ADDR002 | ADDR301 | 42.5 | 2025-01-12 |
Sanctioned Entities
| address_id | entity_name | sanctions_list | designation_date |
|---|---|---|---|
| ADDR300 | Garantex | OFAC-SDN | 2022-04-05 |
| ADDR301 | Garantex | OFAC-SDN | 2022-04-05 |
Write your PQL query
Describe what to predict in 2-3 lines — Kumo handles the rest
PREDICT LIST_DISTINCT(ON_CHAIN_TRANSFERS.TO_ADDRESS WHERE SANCTIONED_ENTITIES.SANCTIONS_LIST = "OFAC-SDN", 0, 30, days) FOR EACH ADDRESSES.ADDRESS_ID
Prediction output
Every entity gets a score, updated continuously
| ADDRESS_ID | CLASS | SCORE | TIMESTAMP |
|---|---|---|---|
| ADDR001 | ADDR300 | 0.92 | 2025-02-01 |
| ADDR002 | ADDR301 | 0.84 | 2025-02-01 |
Understand why
Every prediction includes feature attributions — no black boxes
Address ADDR001
Predicted: 92% probability of sending to ADDR300 (Garantex)
Top contributing features
Transfer amount to ADDR300
15.0 ETH
38% attribution
Sanctioned entity name
Garantex (OFAC-SDN)
27% attribution
Designation date
2022-04-05
16% attribution
Address entity_type
individual
12% attribution
Address first_seen recency
9 months
7% attribution
Feature attributions are computed automatically for every prediction. No separate tooling required. Learn more about Kumo explainability
PQL Documentation
Learn the Predictive Query Language — SQL-like syntax for defining any prediction task in 2-3 lines.
Python SDK
Integrate Kumo predictions into your pipelines. Train, evaluate, and deploy models programmatically.
Explainability Docs
Understand feature attributions, model evaluation metrics, and how to build trust with stakeholders.
Bottom line: Block transactions to sanctioned exchanges before broadcast. OFAC penalties reach $10M per violation. Prediction is the only way to comply proactively.
Related scenarios
Explore more fraud predictions
Topics covered
One Platform. One Model. Predict Instantly.
KumoRFM
Relational Foundation Model
Turn structured relational data into predictions in seconds. KumoRFM delivers zero-shot predictions that rival months of traditional data science. No training, feature engineering, or infrastructure required. Just connect your data and start predicting.
For critical use cases, fine-tune KumoRFM on your data using the Kumo platform and Data Science Agent for 30%+ higher accuracy than traditional models.
Book a demo and get a free trial of the full platform: data science agent, fine-tune capabilities, and forward-deployed engineer support.
