Multivariate time series prediction via temporal classification

In this paper, we study a special form of time-series prediction, viz. the prediction of a dependent variable taking discrete values. Although in a real application this variable may take numeric values, the users are usually only interested in its value ranges, e.g. normal or abnormal, not its actual values. In this work, we extended two traditional classification techniques, namely the naive Bayesian classifier and decision trees, to suit temporal prediction. This results in two new techniques: a temporal naive Bayesian (T-NB) model and a temporal decision tree (T-DT). T-NB and T-DT have been tested on seven real-life data sets from an oil refinery. Experimental results show that they perform very accurate predictions.