Automatic Discovery of Multi-perspective Process Model using Reinforcement Learning

  title={Automatic Discovery of Multi-perspective Process Model using Reinforcement Learning},
  author={Sunghyun Sim and Ling Liu and Hyerim Bae},
—Process mining is a methodology for derivation and analysis of processes models based on the event log. When process mining is employed to analyze business processes, the process discovery step, the conformance checking step, and the enhancements step are repeated. If a user wants to analyze a process from multiple perspectives (such as activity perspectives, originator perspectives, and time perspectives), the above procedure, inconveniently, has to be repeated over and over again. Although… 

Figures and Tables from this paper



Process mining: discovering and improving Spaghetti and Lasagna processes

This invited keynote paper demonstrates that process mining can be used to discover a wide range of processes ranging from structured processes (Lasagna processes) to unstructured processes (Spaghetti processes), and presents the L* life-cycle model consisting of five phases.

Automated Discovery of Process Models from Event Logs: Review and Benchmark

The results highlight gaps and unexplored tradeoffs in the field, including the lack of scalability of some methods and a strong divergence in their performance with respect to the different quality metrics used.

Fuzzy Mining - Adaptive Process Simplification Based on Multi-perspective Metrics

A new process mining approach is proposed that is configurable and allows for different faithfully simplifiedviews of a particular process, just like different roadmaps provide suitable abstractions of reality.

Process mining techniques and applications - A systematic mapping study

Statistical Verification of Process Model Conformance to Execution Log Considering Model Abstraction

A statistical verification method based on the Kolmogorov–Smirnov (K–S) test to judge whether two different log datasets follow the same process model, which can be easily extended to determinations that process execution actually follows a process model.

Service Mining: Using Process Mining to Discover, Check, and Improve Service Behavior

This paper focuses on the opportunities and challenges for service mining, i.e., applying process mining techniques to services and discusses the guiding principles and challenges listed in the process mining manifesto and also highlights challenges specific for service-orientated systems.

Multilevel Process Mining for Financial Audits

A process mining algorithm that creates precise and fitting process models to prevent false negative and false positive audit results, accepts specific unlabeled event logs as input, and considers data relationships for inferring the control flow is introduced.

Discovering Block-Structured Process Models from Event Logs - A Constructive Approach

This work provides an extensible framework to discover from any given log a set of block-structured process models that are sound and fit the observed behaviour, and gives sufficient conditions on the log for which the algorithm returns a model that is language-equivalent to the process model underlying the log, including unseen behaviour.

Automatic Conversion of Event Data to Event Logs Using CNN and Event Density Embedding

An event log–converting algorithm based on the convolutional neural network was developed with a new embedding method called Event Density Embedding (EDE) that is expected that business experts will be able to easily apply the method to process mining technology by utilizing system-derived event data.

Bagging Recurrent Event Imputation for Repair of Imperfect Event Log With Missing Categorical Events

This paper proposes a new categorical event imputation method that can restore missing categorical events by learning the structural features between observed events in the event log and demonstrates that the restoration performance was greatly improved.