Reliable analysis of performance problems and their root causes requires data of a high quality to understand how cases were handed from one employee to another and how they were processed in queues. However, the recorded event data is often of lower quality, e.g., information about queues is missing. The objective of this project is to infer missing event data and event attributes to enable performance and root cause analysis. The key idea is to align recorded event data with a rich process model derived from domain knowledge, describing the process, resource, and queue behavior. This requires creating a semantic model of the processes on the level that enables the automatic construction and analysis of the event knowledge graph.
During the project, the following steps are to be done:
- Obtain an initial understanding of the Incident and Task processes of the ITSM process through interviewing domain experts at ServiceNow
- Design a process model describing these processes, including their queue and resource dimensions.
- Evaluate the model with the domain experts
- Extend the ITSM process model into a simulation model for generating event logs of the process in a variety of scenarios that include Service Level Agreement (SLA) violation.
- Develop and implement the method for Root Cause Analysis (RCA) of SLA violation
- Evaluate the method on the generated log and validate the results with the domain experts
Depending on the remaining time, further evaluation is possible on real ITSM process datasets.
As an outcome, we aim to obtain:
- The formal definition of a process model,
- The method for SLA RCA and its prototype implementation in Java or Python.
The resulting process model will be used in the Process Optimization (PO) product of the ServiceNow platform for inferring missing information about the queue behavior, and for providing extra domain knowledge about processes for PO algorithms. The method for SLA RCA will be implemented as a PO process analysis feature.
During the project, the student will be part of a team developing PO. The student will participate in standup meetings and demo sessions, interview product managers and domain experts, and validate obtained results with them.
- Data science and algorithmic skills
- Java or Python programming skills
- Dirk Fahland. Describing behavior of processes with many-to-many interactions. In Susanna Donatelli and Stefan Haar, editors, Application and Theory of Petri Nets and Concurrency – 40th International Conference, PETRI NETS 2019, Aachen, Germany, June 23-28, 2019, Proceedings, volume 11522 of Lecture Notes in Computer Science, pages 3–24. Springer, 2019.
- Fahland, D., Denisov, V. and van der Aalst, W., 2021. Inferring Unobserved Events in Systems With Shared Resources and Queues. Fundamenta Informaticae, 183(3-4), pp.203-242.
At ServiceNow, our technology makes the world work for everyone, and our people make it possible. We move fast because the world can’t wait, and we innovate in ways no one else can for our customers and communities. By joining ServiceNow, you are part of an ambitious team of change makers who have a restless curiosity and a drive for ingenuity. We know that your best work happens when you live your best life and share your unique talents, so we do everything we can to make that possible. We dream big together, supporting each other to make our individual and collective dreams come true. The future is ours, and it starts with you. With more than 7,400+ customers, we serve approximately 80% of the Fortune 500, and we’re on the 2022 list of FORTUNE World’s Most Admired Companies®.