Incident detection
Related terms
Anomaly detection
Anomaly detection identifies data points or patterns that deviate from an established baseline of normal behavior. Methods range from static statistical thresholds, which flag values beyond a fixed range, to seasonal or time-series decomposition, which accounts for expected cyclical variation, to unsupervised machine learning models that learn normal patterns without labeled examples. In CX, it flags unexpected spikes in ticket volume, negative sentiment, or a specific contact reason before they become widespread. Thresholds set too tightly generate false positives and alert fatigue, and real problems get buried in noise. OnClarity’s Voice of Customer includes real-time alerting that can flag unusual shifts in feedback volume or sentiment as they surface.
Trend detection
Trend detection identifies a sustained directional change in the volume or sentiment of a topic over time, measured against a historical baseline adjusted for normal seasonal variation. It differs from anomaly detection, which flags a single unexpected spike or data point rather than a gradual shift. For example, mentions of a failed login step can climb steadily over three weeks. That's a pattern too slow for any one agent to notice until it crosses a threshold worth escalating. OnClarity's Voice of Customer tracks these patterns continuously, raises alerts, and pushes feedback topics into Slack, Jira, or Linear. It builds on topic clustering and complements anomaly detection rather than replacing it.
Voice of customer
Voice of customer is the discipline of turning reviews, support tickets, surveys, and conversations into operational decisions. The distinguishing feature of a working programme is the closed loop: findings reach the team that can fix the cause, and the resulting change is measured against contact volume.
