Described is system for predicting significant events using a progress curve model. The system first determines Z-score values for a predetermined period of a time series to generate a Z-score time series. The Z-score time series are partitioned into a plurality of E-periods to define time frames for progress curve model (PCM) fitting. An E-period is defined as a period of escalation and de-escalation. Finally, a future event is predicted based on an absolute Z-score value that is greater than or equal to a predetermined number.
