Editing AI for Anti-Money Laundering (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''Transaction anomaly detection with graph features:'''
<syntaxhighlight lang="python">
import pandas as pd
import numpy as np
import networkx as nx
from sklearn.ensemble import IsolationForest, GradientBoostingClassifier
from sklearn.preprocessing import StandardScaler

def build_transaction_graph(transactions_df: pd.DataFrame) -> nx.DiGraph:
    """Build directed transaction graph from financial transaction records."""
    G = nx.DiGraph()
    for _, tx in transactions_df.iterrows():
        G.add_edge(tx['sender_id'], tx['receiver_id'],
                   amount=tx['amount'], date=tx['date'],
                   tx_id=tx['transaction_id'])
    return G

def extract_network_features(G: nx.DiGraph, entity_id: str) -> dict:
    """Extract AML-relevant network features for an entity."""
    if entity_id not in G:
        return {}
    return {
        'in_degree': G.in_degree(entity_id),
        'out_degree': G.out_degree(entity_id),
        'in_out_ratio': G.in_degree(entity_id) / (G.out_degree(entity_id) + 1),
        'pagerank': nx.pagerank(G).get(entity_id, 0),
        'clustering': nx.clustering(G.to_undirected(), entity_id),
        # Fan-in/fan-out: many senders → one receiver (concentration)
        'unique_senders': len(list(G.predecessors(entity_id))),
        'unique_receivers': len(list(G.successors(entity_id))),
        # Circular flows: A → B → A (laundering signature)
        'reciprocal_edges': sum(1 for n in G.predecessors(entity_id)
                                if G.has_edge(entity_id, n)),
        # Transaction velocity
        'avg_in_amount': np.mean([d['amount'] for _, _, d in G.in_edges(entity_id, data=True)]) if G.in_degree(entity_id) > 0 else 0,
    }

def detect_structuring(transactions_df: pd.DataFrame, threshold=10000) -> pd.DataFrame:
    """Detect structuring (breaking transactions to stay under reporting threshold)."""
    df = transactions_df.copy()
    df['date'] = pd.to_datetime(df['date'])
    df['window_total'] = (df.groupby('sender_id')
                           .rolling('3D', on='date')['amount']
                           .sum().reset_index(0, drop=True))
    # Flag: multiple sub-threshold transactions summing to over threshold
    suspicious = df[(df['amount'] < threshold) &
                    (df['window_total'] > threshold * 0.9)]
    return suspicious

# ML model combining transaction + network features
features = ['amount', 'in_degree', 'out_degree', 'pagerank', 'reciprocal_edges',
            'unique_senders', 'unique_receivers', 'tx_velocity_7d', 'avg_amount',
            'counterparty_risk_score', 'country_risk', 'pep_flag']

# Gradient boosting on labeled SAR data (rare: ~1% positive rate)
model = GradientBoostingClassifier(n_estimators=200, scale=True,
                                   subsample=0.8, learning_rate=0.05)
# Risk scoring: output SAR probability, rank alerts by risk score
</syntaxhighlight>

; AML AI tools
: '''Network analytics''' → Quantexa, Graph for AML (Microsoft), DataWalk
: '''Transaction monitoring''' → NICE Actimize, Temenos Financial Crime Mitigation
: '''Adverse media / KYC''' → Dow Jones Risk & Compliance, Refinitiv World-Check, ComplyAdvantage
: '''Sanctions screening''' → Firco Compliance Link, ACI Worldwide, LexisNexis Risk Solutions
: '''SAR analytics''' → FinCEN BSA/AML analytics, Babel Street, Palantir AML
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">