Description
Reliable analysis of performance problems and their Root Causes (RCs) requires understanding if a case was delayed by other cases in employees’ or teams’ queues of the same process and/or by cases of other processes. The former is described by the multiple execution single object process dimension, and the latter by the single execution multiple objects process dimension, studied by object-centric Process Mining (PM).
This project objective is to create a method for RC analysis of performance problems, given a process model and a multi-entity event log with information about the queues and related processes, aligned with the model. The key idea is to identify relevant features, derive them from the event log, and apply eXplainable AI (XAI) for inferring RCs.
During the project, the following steps are to be done:
- Obtain an initial understanding of the ITSM process and actual problems of RC analysis through interviewing domain experts at ServiceNow and studying existing process models.
- Improve existing process models if required.
- Identify relevant features and create training datasets.
- Choose and apply suitable XAI techniques.
- Evaluate the RCs with the domain experts.
- Repeat steps 2-5 till the required accuracy is achieved.
The resulting method for RC performance analysis will be used in the PM component of the ServiceNow platform. The student will be part of the team developing this component, participate in team meetings and demo sessions, interview product managers and domain experts, and validate the obtained results with them.
Prerequisites
- Data science, ML, and algorithmic skills
- Java or Python programming skills
Pointers
- https://www.servicenow.com/products/process-optimization.html
- https://multiprocessmining.org/
- 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.
About ServiceNow
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 7,700+ customers, we serve approximately 85% of the Fortune 500®, and we’re proud to be one of FORTUNE 100 Best Companies to Work For® and World’s Most Admired Companies™ .