Discriminative Sequential Pattern Mining for Software Failure Detection

Software event sequence is a software behavior trace which is produced when software is running. Analyzing the database of software event sequences, we present a novel method to distinguish normal and abnormal behaviors for the purpose of software failure detection. Sequence classification has been a challenge task since sequences have the high-order temporal characteristics and make the number of patterns extremely massive. We select the frequent closed unique iterative patterns as candidate features, mine out the discriminative binary and numerical patterns for sequence classification, and further give an insight into the discriminative power improvement by feature combinations. The experimental results on synthetic and real-life datasets show the validity of our method.