Open-Source Process Mining Tools

As part of the work on my PhD project Multi-perspective Process Mining I developed several tools and open-source software packages for the process mining framework ProM and it RapidMiner variant RapidProM. Some of the software is also available outside of ProM at my personal GitHub page.

Most of the ProM packages and plug-ins are included in one of the stable release versions, which are released every year to help keeping results reproducable. However, since any non-trivial software contains errors, which is especially so for academic prototypes, I advise to use the latest version available in the nightly builds of the ProM framework. It is sufficient to install the nightly build version once and, then, update the packages regularly. In fact, if you do not update packages you can enjoy a stable version using a nightly build installation. So, usually, there is not reason to install one of the frozen version unless you want to reproduce some result reported to be obtained with a specific ProM version.

Interactive Data-aware Heuristic Miner (iDHM)


An interactive data-aware process discovery tool based on the ideas of the heuristics miner combined with classification techniques. The iDHM implements a process discovery method that uses the data attributes to distinguish infrequent paths from random noise by using classification techniques. Data- and control-flow of the process are discovered together.

ProM Package: DataAwareCNetMiner
ProM Plug-ins: Interactive Data-aware Heuristic Miner
Documentation: Online Manual
Sources: ProM SVN
Related Publications:


Multi-perspective Process Explorer (MPE)


An interactive tool integrating conformance checking (fitness & precision), decision mining and performance analysis for multi-perspective process models.

ProM Package: DataAwareExplorer
ProM Plug-ins: Multi-perspective Process Explorer
Documentation: Package Manual
Sources: ProM SVN
Related Publications:


Pattern-based Event Log Abstraction


A supervised abstraction method based on behavioral activity patterns that capture domain knowledge on the relation between activities and events. Through an alignment between the activity patterns and the low-level event logs an abstracted event log is obtained. Events in the abstracted event log correspond to instantiations of recognizable activities.
ProM Package: LogEnhancement

ProM Plug-ins: Log Abstraction - Abstract Log based on Patterns
RapidProM Operators: Log Abstraction
Documentation: to be done
Sources: ProM SVN · RapidProM
Publications:


Event Log Explorer


An alternative event log visualization, which handles large event logs efficiently and provides a SQL-like query engine.

ProM Package: LogEnhancement
ProM Visualizer: Explore Event Log
Documentation: to be done
Sources: ProM SVN


XESLite


An efficient XES implementation to be used with medium-sized event logs that are too large for in-memory processing with the OpenXES implementation.

ProM Package: XESLite
ProM Plug-ins: XES importers: MapDB, In-Memory, Automaton-based
Documentation: Package Manual
Sources: ProM SVN · Github
Publications:

Comments are closed for this post