Money-laundering rings,
detected through the graph.
A graph-native AML platform that ingests a transaction network, engineers 14 topology + flow features, trains a gradient-boosted classifier with ROC-AUC 0.87, and surfaces explainable node-level alerts with path-level reason codes. Every score is case-openable in a live React investigator UI.
Trained LightGBM with honest metrics
hold-out split · reported as-isTop suspects ranked in real time
POST /api/v1/score| Rank | Node | Score | Band |
|---|---|---|---|
| Fetching live scores… | |||
From raw edges to explainable case
deterministic · reproducibleIngest
Load CSV/JSONL edges into a NetworkX MultiDiGraph. Optional push to Neo4j for Cypher-native exploration.
Featurize
Compute per-node topology and flow features: degree, PageRank, betweenness, triads, ego density, txn flow.
Train
Stratified train/val split, LightGBM binary classifier, metrics persisted to SQLite. One command.
Score
Apply model to all nodes; return Top-K suspects with calibrated probability and band-level classification.
Explain
Local surrogate + path explanations. What-if operators let analysts simulate edge addition/removal live.
Open the investigator console.
Full React dashboard with score table, case explorer, graph mini-view, and what-if simulator. Click a suspect, see their 1-hop neighborhood, read the reason codes, run a local surrogate explanation.