kpi-anomaly-triage

When to invoke

• When monitoring weekly/daily KPI dashboards for sudden changes.
• When preparing an investigation checklist for metric movements.

Inputs needed

• --input: Path to a CSV file with columns date (YYYY-MM-DD) and value.
• Optional --window: Rolling window size in days (default 14).
• Optional --z: Z-score threshold (default 3.0).
• Optional --out: Path to write a JSON report.

Workflow

1. Parse dates and values; sort by date.
2. Compute rolling mean and standard deviation.
3. Flag points with [ z = \frac{x - \mu}{\sigma} ] above threshold.
4. Summarize recent anomalies and basic context (last 7 days trend).