STREAM[ OVERVIEW ]

Real-time Bitcoin transaction risk scoring. Live transactions are pulled from the mempool, scored by ML models for illicit activity signals, and logged to an audit trail. High-risk transactions are automatically flagged for compliance review.

This page streams live Bitcoin mempool data, scores each transaction, and displays the results below. The feed updates automatically via SSE.

MEMPOOL STATUS[ LIVE ]

Live scoring uses a mempool-features heuristic. The trained XGBoost model is available at /illicit for 166-feature input.

RISK THRESHOLD
0.50

Lower the threshold to trigger more alerts for demo purposes.

SCORING FEED[ STREAMING ]

Live mempool transactions scored in real-time.

TIME
TX_ID
SIZE
FEE_RATE
RISK
LABEL
ANOMALY
ALERT QUEUE[ MONITORING ]

Flagged transactions for compliance review.

Time TX ID Score Status
ALERT DETAIL[ SELECT_ALERT ]

Select an alert to view SHAP explanation and compliance narrative.

FEEDBACK LOOP[ LEARNING ]

Review alerts as TP/FP above, then retrain the scoring model on your labels.

DRIFT MONITOR[ WATCHING ]

Score distribution stability — detects when the mempool shifts away from baseline.

ONLINE METRICS[ TRACKING ]

Live precision, recall, F1, ROCAUC — cumulative and rolling window.

ANOMALY DETECTOR[ SCANNING ]

Unsupervised anomaly detection using Half-Space Trees. Learns transaction patterns and flags outliers.

MODEL RACE[ RACING ]

3 online classifiers competing in real-time: LogisticRegression vs HoeffdingTree vs GaussianNB.

STANDINGS

CONVERGENCE