Earthquake forecasting is known to be a challenging problem because no single prediction method can claim to have the best accuracy at all times. Earthquake data when viewed as a time series over a long time, exhibits a complex pattern that is composed of a mix of statistical features. A single prediction algorithm often does not yield an optimal forecast by analyzing over a long series that is composed of a large variety of features. A new analytic model is proposed that allows these mixed features from the time series to be automatically extracted by a computer program, and fed into a decision tree classifier for choosing an appropriate method for the current forecasting task. The motivation behind this concept is to let the data decide which prediction algorithm should be adopted, adaptively across different periods of the time series. The contribution of this paper is twofold: (1) an automatic forecasting model which is very suitable for real-time earthquake monitor is proposed, and (2) an investigation on how different features of the data series are coupled with different prediction algorithms for the best possible accuracy.