Sequential Anomaly Detection Techniques in Business Processes

Many companies use information systems to manage their business processes and thereby collect large amounts of transactional data. The analysis of this data offers the possibility of automated detection of anomalies, i.e. flaws and faults, in the execution of the process. The anomalies can be related not only to the sequence of executed activities but also to other dimensions like the organization or the person performing the respective activity. This paper discusses two approaches of detecting the different anomalies types using basic sequential analysis techniques. Besides the classical one-dimensional approach, a simple approach to use multiple dimensions of the process information in the sequential analysis is discussed and evaluated on a simulated artificial business process.