Applying Inductive Logic Programming to Process Mining
The management of business processes has recently received a lot of attention. One of the most interesting problems is the description of a process model in a language that allows the checking of the compliance of a process execution (or trace) to the mod
- PDF / 412,441 Bytes
- 15 Pages / 430 x 660 pts Page_size
- 73 Downloads / 217 Views
The management of business processes has recently received a lot of attention. One of the most interesting problems is the description of a process model in a language that allows the checking of the compliance of a process execution (or trace) to the model. In this paper we propose a language for the representation of process models that is inspired to the SCIFF language and is an extension of clausal logic. A process model is represented in the language as a set of integrity constraints that allow conjunctive formulas as disjuncts in the head. We present an approach for inducing these models from data: we define a subsumption relation for the integrity constraints, we define a refinement operator and we adapt the algorithm ICL to the problem of learning such formulas. The system has been applied to the problem of inducing the model of a sealed bid auction and of the NetBill protocol. The data used for learning and testing were randomly generated from correct models of the processes. Keywords: Process Mining, Learning from Interpretations, Business Processes, Interaction Protocols.
1
Introduction
Every organization performs a number of business processes in order to achieve its mission. Complex organizations are characterized by complex processes, involving many people, activities and resources. The performances of an organization depend on how accurately and efficiently it enacts its business processes. Formal ways of representing business processes have been studied in the area of business processes management (see e.g. [1]), so that the actual enactment of a process can be checked for compliance with a model. Recently, the problem of automatically inferring such a model from data has been studied by many authors (see e.g. [2,3,4]). This problem has been called Process Mining or Workflow Mining. The data in this case consists of execution traces (or histories) of the business process. The collection of such data is made possible by the facility offered by many information systems of logging the activities performed by users. H. Blockeel et al. (Eds.): ILP 2007, LNAI 4894, pp. 132–146, 2008. c Springer-Verlag Berlin Heidelberg 2008
Applying Inductive Logic Programming to Process Mining
133
In this paper, we propose a novel representation language for describing process models and an approach to Process Mining that uses learning from interpretations techniques from ILP. The language is inspired to the SCIFF one [5] and extends clausal logic by allowing more complex formulas as disjuncts in the head of clauses. We show how an execution trace can be represented as an interpretation and how we can use our language to check its compliance with the model. Thus we can cast a process mining problem as a learning from interpretations problem. In particular, we considered the discriminant problem that is solved by ICL [6], where we have positive and negative interpretations and we want to find a clausal theory that discriminates the two. In our case we assume that we have compliant and non compliant traces of execution of a
Data Loading...
