Discovery of probabilistic rules for prediction
Keith C. C. Chan, Andrew K. C. Wong, David Chiu · 2003
An inductive learning algorithm is presented for analyzing the inherent patterns in a sequence and for predicting future objects based on these patterns. This algorithm is divided into three phases: detection of underlying patterns in a sequence of objects; construction of rules, based on the detected patterns, that describe the generation process of the sequence; and use of these rules to predict the characteristics of the future objects. The learning algorithm has been implemented in a program known as the OBSERVER, and it has been tested with both simulated and real-life data. The experimental results show that the OBSERVER is capable of discovering hidden patterns and explaining the behavior of certain sequence-generating processes that a user is not immediately aware of or fully understood. For this reason, the OBSERVER can be used to solve complex real-world problems where predictions have to be made in the presence of uncertainty.>