Trend 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.
Topic clustering
Topic clustering groups conversations by theme to size the drivers behind contact volume, without requiring an analyst to define categories in advance. Because clusters emerge from what customers actually said, the method surfaces new issues that a fixed intent taxonomy would file under a generic other.
Sentiment analysis
Sentiment analysis scores the emotional tone of a conversation to flag risk and measure experience without waiting for a survey response. Applied across every contact rather than a sampled few, it covers the large majority of customers who never complete a satisfaction survey at all.
