Anomaly Impact Alert

Anomaly Impact Alert — a lightweight Python toolkit for detecting anomalies, forecasting metrics, explaining deviations, and sending alerts (e.g. via Telegram)

Purpose

This library helps analytics and monitoring teams automatically:

• Detect abnormal metric values in time-series data
• Forecast expected ranges (with confidence intervals)
• Explain the drivers behind changes (countries, platforms, etc.)
• Send structured alerts to Telegram

Demo Notebook

Anomaly Impact Alert is a lightweight Python toolkit for:

• Anomaly detection (Z-Score, CI, STL, SESD, LOF, Isolation Forest, and more)
• Forecasting metrics (Prophet, ETS, STL ensemble)
• Explaining deviations (impact decomposition by segments)
• Sending alerts (e.g., via Telegram)

This notebook demonstrates how to use anomaly_impact_alert in practice:

• Data preparation
• Anomaly detection workflow
• Time-series forecasting
• Contribution analysis across segments
• Automated alert generation and explanations

Try it in Google Colab: 👉 Open in Colab

Example Output

Detection visualization

Shows detected anomalies (red dots), confidence intervals, and model outputs:

Telegram alert

Example of an automatically formatted alert with top contributing segments:

Quick Start

pip install anomaly_impact_alert

Try it in Google Colab: 👉 Open in Colab

Modules Overview

Dependencies

pandas, numpy, scikit-learn, matplotlib, prophet, tqdm, requests, python-telegram-bot

License

MIT © 2025 Alexey Voronko