Real-time Predictive Monitoring for Business Processes

FEATURES

TRAIN PREDICTIVE MODELS

Train machine learning models for various process performance indicators, such as remaining time or expected workload

EVALUATE PREDICTION ACCURACY

Check how accurate your models are at certain time points

MONITOR PROCESS IN REAL-TIME

Check the current and predicted performance of ongoing process instances

VISUALIZE SUMMARY STATISTICS

Produce visualizations for current and expected values of performance indicators

Nirdizati is an open-source web-based predictive process monitoring engine for running business processes. 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). On the backend, Nirdizati uses predictive models pre-trained using data about historical process execution.

Nirdizati consists of two components: Nirdizati Training and Nirdizati Runtime. The former takes as input a business process event log and produces one or more predictive models, which can then be deployed in Nirdizati Runtime. Once a model is deployed, Nirdizati Runtime listens to a stream of events coming from an information system supporting the process, and produces a stream of predictions. These predictions are then visualized in a continuously updated web dashboard.

Screencast

Project team

Nirdizati is a joint project developed by a group of institutions around the globe:

QUEENSLAND UNIVERSITY OF TECHNOLOGY, AUSTRALIA

FONDAZIONE BRUNO KESSLER, ITALY

Nirdizati’s development team welcomes contributions from universities and companies.
If you wish to contribute to our effort, please get in touch with us using the contact form below:

Get in touch