---
title: "Time-Series Anomaly Detector"
method: POST
path: "/v1/tools/detect_timeseries_anomalies"
tags: ["TODO_TAGS_REVIEW"]
---

# Time-Series Anomaly Detector

`POST /v1/tools/detect_timeseries_anomalies`

## Request

- Base URL: `https://ainumbers.co`
- URL: `https://ainumbers.co/v1/tools/detect_timeseries_anomalies`
- Auth: none declared

Rolling-window z-score and STL-style seasonal decomposition anomaly detection on synthetic payment volume time series. Control chart (UCL/LCL 3σ), trend/seasonal/residual panel decomposition, anomaly flag table with severity, naïve ARIMA-lite 30-period forecast. Chains from SIM-03 (Basel RWA Scenario Modeler). Feeds RCA-01 (FRTB IMA). DORA Art.17 monitoring / EBA GL/2021/03 operational risk / PSD2 Art.96 fraud reporting.

**Tool URL:** https://ainumbers.co/chaingraph/ml-03-timeseries-anomaly-detector.html
**AP2/Policy Mandate export:** yes

## Request body

- object
  - `nAnomalies` number, required
  - `nPeriods` number, required
  - `seasonPeriod` number, required
  - `seed` number, required
  - `trendType` unknown, required
  - `windowSize` number, required
  - `zThreshold` number, required

## Response `200`

Successful tool execution result

- object
  - `anomalies_flagged` integer
  - `flag_rate` number
  - `flagged_periods` object[]
    - `direction` string
    - `severity` string
    - `t` integer
    - `z` number
  - `high_severity_flags` integer
  - `max_abs_z_score` number
  - `medium_severity_flags` integer
  - `n_periods` integer
  - `verdict` string

---

[API](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite.md) · [All operations](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite/llms.txt) · [OpenAPI document](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite/revisions/b462e4f5bb28?raw)