PyOD — Outlier & Anomaly Detection
A comprehensive Python toolkit of 60+ outlier-detection algorithms, widely applied to financial fraud and anomaly detection.
PyOD
PyOD is one of the most widely used Python libraries for detecting anomalous data points, offering more than 60 detection algorithms under a single, scikit-learn-style API. While general-purpose, it is a staple for financial fraud and anomaly detection, where flagging unusual transactions, accounts, or market behavior is the core task.
Key features
- 60+ detectors from classical (LOF, Isolation Forest, KNN) to deep learning (AutoEncoder, DeepSVDD)
- Unified
fit/predict/decision_functionAPI compatible with scikit-learn - Model-combination utilities (averaging, maximization) for robust ensembles
- Benchmarks and thresholding helpers for setting anomaly cutoffs
- Extensively documented, tested, and cited across academia and industry
A typical fraud workflow fits a detector on transaction features, then scores new records; high anomaly scores surface likely-fraudulent activity for review.
Curated mirror of the open-source PyOD (BSD-2-Clause). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/pyod-anomaly-fraud-detection/check). Click a policy:
Consume PyOD — Outlier & Anomaly Detection programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/pyod-anomaly-fraud-detection
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/pyod-anomaly-fraud-detection/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add pyod-anomaly-fraud-detection
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/pyod-anomaly-fraud-detection/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "pyod-anomaly-fraud-detection" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.