Isolation Forest anomaly detection on synthetic transaction batches. Scores each transaction across four features (amount, hour-of-day, counterparty frequency, recency) using a 10-tree forest with subsampled isolation. Anomaly score near 1.0 = isolated quickly = anomalous. All computation is client-side — no transaction data transmitted. Chains from ART-10 (AMLA typology scoring).
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.
Run the AINumbers MCP tool `detect_transaction_anomalies`. Task: Run isolation-forest anomaly detection on transaction features and returns a risk_control mandate with anomaly scores, decision boundary, and chain-ready AP2 artifact.
Call it with arguments: {"policy_parameters":{"n_transactions":32,"contamination_rate":0.05,"seed":42,"n_trees":2,"subsample_size":16,"threshold":0.6}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/ml-01-isolation-forest.html#p=v1.H4sIAAAAAAAA_wFpAJb_eyJuX3RyYW5zYWN0aW9ucyI6MzIsImNvbnRhbWluYXRpb25fcmF0ZSI6MC4wNSwic2VlZCI6NDIsIm5fdHJlZXMiOjIsInN1YnNhbXBsZV9zaXplIjoxNiwidGhyZXNob2xkIjowLjZ9fdwVimkAAAA