My paper Prediction of business process durations using non-Markovian stochastic Petri nets with Mathias Weske was accepted for publication in the Information Systems journal of Elsevier.
You can find the preprint version in the publications area.
Or get a free author’s copy now!
Companies need to efficiently manage their business processes to deliver products and services in time. Therefore, they monitor the progress of individual cases to be able to timely detect undesired deviations and to react accordingly. For example, companies can decide to speed up process execution by raising alerts or by using additional resources, which increases the chance that a certain deadline or service level agreement can be met. Central to such process control is accurate prediction of the remaining time of a case and the estimation of the risk of missing a deadline.
To achieve this goal, we use a specific kind of stochastic Petri nets that can capture arbitrary duration distributions. Thereby, we are able to achieve higher prediction accuracy than related approaches. Further, we evaluate the approach in comparison to state of the art approaches and show the potential of exploiting a so far untapped source of information: the elapsed time since the last observed event. Real-world case studies in the financial and logistics domain serve to illustrate and evaluate the approach presented.
My paper with Gjergji Kasneci on Temporal Anomaly Detection in Business Processes has been accepted to BPM 2014.
The paper describes an approach to detect anomalies in the timestamps of events that happen during process execution. The approach is based on historical observations of usual behavior and uses a stochastic model to find outliers in a non-parametric way. It helps process analysts to identify and filter errors from process logs, and also to distinguish between measurement errors (where only one timestamp is the outlier) and real delays (where succeeding activities are also shifted).
The analysis of business processes is often challenging not only because of intricate dependencies between process activities but also because of various sources of faults within the activities. The automated detection of potential business process anomalies could immensely help business analysts and other process participants detect and understand the causes of process errors.
This work focuses on temporal anomalies, i.e., anomalies concerning the runtime of activities within a process. To detect such anomalies, we propose a Bayesian model that can be directly inferred form the Petri net representation of a business process. Probabilistic inference on the above model allows the detection of non-obvious and interdependent temporal anomalies.