Automated Anomaly Detection for Message Volume

The system analyzes message volume only and does not consider transaction amount, content, or timing. Detection focuses on whether expected transaction activity occurs, rather than on the success or failure of individual transactions.

For each eligible trading partner and document type, the system establishes an expected volume range based on historical activity. A daily detection process compares actual message counts to this expected range.

When actual volume falls outside the expected range, the system records an anomaly. Only anomalies that fall outside defined variation thresholds are made available for review, helping reduce noise and focus attention on meaningful changes.

Anomaly detection is designed to highlight what changed in message activity. It provides visibility into unusual volume patterns but does not determine the cause of the change or recommend corrective actions.

Anomaly detection runs automatically for trading partner and document‑type combinations that meet minimum historical data, volume, and duration thresholds.

Once a partner and document type become eligible, detection continues for that combination going forward.

No manual setup or configuration is required.

Detected anomalies are available in Activity > Anomalies, where you can:

• View anomalies by trading partner and document type
• See when each anomaly occurred
• Compare actual message counts to expected volume ranges
• Identify whether volume was higher or lower than expected

A timeline view provides additional context by showing anomalies alongside historical activity, helping identify trends or isolated deviations.

See View detected message‑volume anomalies.

In addition to the in‑product view, Cleo Integration Cloud sends a daily email summary highlighting anomalies detected during the previous 24-hour period.

These notifications provide a starting point for review, reducing the need for continuous dashboard monitoring.