The Runtime component of Nirdizati provides a dashboard-based predictive process monitoring engine. The dashboard is updated periodically based on incoming streams of events. However, unlike classical monitoring dashboards, Nirdizati does not focus on showing the current state of business process executions, but also their future state (e.g. when will each case finish).
The dashboard provides a list of both currently ongoing cases as well as completed cases. For each case, it is also possible to visualize a range of summary statistics including the number of events in the case, its starting time and the time when the latest event in the case has occurred. For the ongoing cases, Nirdizati Runtime provides the predicted values of the performance indicators the user wants to predict. For completed cases, instead, it shows the actual values of the indicators. In addition to the table view, the dashboard offers other visualization options, such as pie charts for case outcomes and bar charts for case durations. For a more detailed description of the user interface, please refer to this page.
Typical users of the Runtime component are process workers and operational managers. They can set some process performance targets and subscribe to a stream of warnings and alerts generated whenever these targets are predicted to be violated. Thus, Nirdizati will hopefully help them make informed, data-driven decisions to get a better control of the process executions. This is especially beneficial for business processes where process participants have more leeway to make corrective actions (for example, in a lead management process).
On the backend, Nirdizati uses predictive models pre-trained using data about historical process execution. These models are based on the methods published in the past couple of years:
- Complex Symbolic Sequence Encodings for Predictive Monitoring of Business Processes In Proceedings of BPM'2015 (source code)
- Predictive Business Process Monitoring with Structured and Unstructured Data In Proceedings of BPM'2016 (source code)
- A Web-Based Tool For Predictive Process Analytics Master's thesis of Kerwin Jorbina (source code)
The latter work resulted in the creation of our sister project, Nirdizati Training.
If you want to install Nirdizati Runtime on your server, please follow these steps:
The Runtime component of Nirdizati is a joint effort by the Software Engineering Research Group of the University of Tartu and the Business Process Management research group of Queensland University of Technology. The development is maintained by Andrii Rozumnyi, Simon Raboczi, Ilya Verenich, Marcello La Rosa and Marlon Dumas, among others. Credits also go to Alireza Ostovar, Dmitriy Velichko, Anastasiia Babash and Alexey Golovin.
Nirdizati’s development team welcomes contributions from universities and companies, as well as from interested individuals! Good pull requests, such as patches, improvements, and new features, are a fantastic help. In order to do that, please follow contribution quide.