Chiara Di Francescomarino

Predictive Monitoring of Business Processes

Modern information systems that support complex business processes generally maintain significant amounts of process execution data, particularly records of events corresponding to the execution of activities (event logs). In this paper, we present an approach to analyze such event logs in order to predictively monitor business constraints during business process execution. At any point during an execution of a process, the user can define business constraints in the form of linear temporal logic rules. When an activity is being executed, the framework identifies input data values that are more (or less) likely to lead to the achievement of each business constraint. Unlike reactive compliance monitoring approaches that detect violations only after they have occurred, our predictive monitoring approach provides early advice so that users can steer ongoing process executions towards the achievement of business constraints. In other words, violations are predicted (and potentially prevented) rather than merely detected. The approach has been implemented in the ProM process mining toolset and validated on a real-life log pertaining to the treatment of cancer patients in a large hospital.

Reasoning on Semantically Annotated Processes

Enriching business process models with semantic tags taken from an ontology has become a crucial necessity in service provisioning, integration and composition. In this paper we propose to represent semantically labelled business processes as part of a knowledge base that formalises: business process structure, business domains, and a set of criteria describing correct semantic labelling. Our approach allows (1) to impose domain dependent constraints during the phase of process design, and (2) to automatically verify, via logical reasoning, if business processes fulfill a set of given constraints, and to formulate queries that involve both knowledge about the domain and the process structure. Feasibility and usefulness of our approach will be shown by means of two use cases. The first one on domain specific constraints, and the second one on mining and evolution of crosscutting concerns.

Reverse Engineering of Business Processes exposed as Web Applications

Business processes are often implemented by means of software systems which expose them to the user as an externally accessible Web application. This paper describes a technique for recovering business processes by dynamic analysis of the Web applications which ex-pose them. This approach does not require full access to internal software artifacts, such as source code or doc-umentation. The business process is instead inferred through analysis of the GUI-forms exercised by the user during the navigation in the Web application which ex-poses the process. The recovered process is then abstracted by clustering its business tasks according to structural or logical criteria.A preliminary experiment has been conducted with the aim of evaluating understandability and readability of the reverse engineered business processes.

Semantically-Aided Business Process Modeling

Enriching business process models with semantic annotations taken from an ontology has become a crucial necessity both in service provisioning, integration and composition, and in business processes management. In our work we represent semantically annotated business processes as part of an OWL knowledge base that formalises the business process structure, the business domain, and a set of criteria describing correct semantic annotations. In this paper we show how Semantic Web representation and reasoning techniques can be effectively applied to formalise, and automatically verify, sets of constraints on Business Process Diagrams that involve both knowledge about the domain and the process structure. We also present a tool for the automated transformation of an annotated Business Process Diagram into an OWL ontology. The use of the semantic web techniques and tool presented in the paper results in a novel support for the management of business processes in the phase of process modeling, whose feasibility and usefulness will be illustrated by means of a concrete example.

Crosscutting Concern Documentation by Visual Query of Business Processes

Business processes can be very large and may contain several different concerns, scattered across the process and tangled with other concerns. Crosscutting concerns are difficult to find and locate, thus making process design and evolution hard.

Clustering-Based Predictive Process Monitoring

The enactment of business processes is generally supported by information systems that record data about each process execution (a.k.a. case). This data can be analyzed via a family of methods broadly known as process mining. Predictive process monitoring is a process mining technique concerned with predicting how running (uncompleted) cases will unfold up to their completion. In this paper, we propose a predictive process monitoring framework for estimating the probability that a given predicate will be fulfilled upon completion of a running case. The framework takes into account both the sequence of events observed in the current trace, as well as data attributes associated to these events. The prediction problem is approached in two phases. First, prefixes of previous (completed) cases are clustered according to control flow information. Second, a classifier is built for each cluster using event data attributes to discriminate between cases that lead to a fulfillment of the predicate under examination and cases that lead to a violation within the cluster. At runtime, a prediction is made on a running case by mapping it to a cluster and applying the corresponding classifier. The framework has been implemented in the ProM toolset and validated on a log pertaining to the treatment of cancer patients in a large hospital.

Supporting Ontology-Based Semantic Annotation of Business Processes with Automated Suggestions

Annotation of Business Processes with semantic tags taken from a domain ontology is beneficial to several activities conducted on Business Processes, such as comprehension, documentation, analysis and evolution. On the other hand, the task of semantically annotating Business Processes is time-consuming and far from trivial. The authors support Business Process designers in the annotation of process elements by automatically suggesting candidate concepts. The annotation suggestions are computed on the basis of a similarity measure between the text information associated with process element labels and the ontology concepts. In turn, this requires support for the disambiguation of terms appearing in ontology concepts, which admit multiple linguistic senses, and for ontology extension, when the available concepts are insufficient.

Semantics-Based Aspect-Oriented Management of Exceptional Flows in Business Processes

Enriching business process models with semantic annotations that are taken from an ontology has become a crucial need in service provisioning, integration and composition, and business processes management. We represent semantically annotated business processes as part of an Web ontology lanuage knowledge base that formalizes the business process structure, the business domain, a set of criteria that describe correct semantic annotations, and a set of constraints that describe requirements on the business process itself. In this paper, we show how the Semantic Web representation and reasoning techniques can be 1) exploited by our aspect-oriented approach to modularize exception-handling (as well as other crosscutting) mechanisms and 2) effectively applied to formalize and automatically verify constraints on the management of exceptional flows (as well as other relevant flows) in business processes. The benefits of the Semantic Web and the aspect-oriented technologies are illustrated in a case study, where exceptional flows are modularized separately and managed at the semantic level due to the proposed approach.

Predictive Business Process Monitoring Framework with Hyperparameter Optimization

Predictive business process monitoring exploits event logs to predict how ongoing (uncompleted) traces will unfold up to their completion. A predictive process monitoring framework collects a range of techniques that allow users to get accurate predictions about the achievement of a goal for a given ongoing trace. These techniques can be combined and their parameters configured in different framework instances. Unfortunately, a unique framework instance that is general enough to outperform others for every dataset, goal or type of prediction is elusive. Thus, the selection and configuration of a framework instance needs to be done for a given dataset. This paper presents a predictive process monitoring framework armed with a hyperparameter optimization method to select a suitable framework instance for a given dataset.

Cluster-based modularization of processes recovered from web applications

Web applications are often used to expose business processes implemented as software systems. This paper describes a technique for recovering business processes based on a dynamic analysis of the applications behavior. The technique described here does not require any access to internal software artifacts of the application, such as source code or documentation. An initial process is inferred to by means of the analysis of execution traces, in which the execution of GUI elements such as forms and links is recorded. The recovered process is then abstracted by clustering its elements according to four different criteria: structural, page‐based, dependency‐based and semantical. A case study has been conducted with the aim of evaluating understandability and readability of the reverse engineered processes as well as the clustering techniques used in refining them. Copyright