Abstract:Abstract. A central problem in the area of Process Mining is to obtain a formal model that represents selected behavior of a system. The theory of regions has been applied to address this problem, enabling the derivation of a Petri net whose language includes a set of traces. However, when dealing with real-life systems, the available tool support for performing such task is unsatisfactory, due to the complex algorithms that are required. In this paper, the theory of regions is revisited to devise a novel tech… Show more
“…We call the model DpL D q for such a smallest log L D a top model M T . For this experiment, we considered the following discovery algorithms: Inductive Miner (IM) [17], Integer Linear Programming miner (ILP) [35], α-algorithm (α) [3], Region miner (RM) [28,4] and flower model, all plug-ins of the ProM framework [14]. The flower model was included as a baseline, as it will reach its top model if L Σ M : it only depends on the presence of activities in the log.…”
Section: Resultsmentioning
confidence: 99%
“…For instance, after a transition system has been constructed from the log, state-based region miner techniques construct a Petri net by folding regions of states into places [4,28]. Typically, statebased region techniques provide rediscoverability guarantees [10], but have problems dealing with parallelism.…”
One of the main challenges in process mining is to discover a process model describing observed behaviour in the best possible manner. Since event logs only contain example behaviour and one cannot assume to have seen all possible process executions, process discovery techniques need to be able to handle incompleteness. In this paper, we study the effects of such incomplete logs on process discovery. We analyse the impact of incompleteness of logs on behavioural relations, which are an abstraction often used by process discovery techniques. We introduce probabilistic behavioural relations that are less sensitive to incompleteness, and exploit these relations to provide a more robust process discovery algorithm. We prove this algorithm to be able to rediscover a model of the original system. Furthermore, we show in experiments that our approach even rediscovers models from incomplete event logs that are much smaller than required by other process discovery algorithms.
“…We call the model DpL D q for such a smallest log L D a top model M T . For this experiment, we considered the following discovery algorithms: Inductive Miner (IM) [17], Integer Linear Programming miner (ILP) [35], α-algorithm (α) [3], Region miner (RM) [28,4] and flower model, all plug-ins of the ProM framework [14]. The flower model was included as a baseline, as it will reach its top model if L Σ M : it only depends on the presence of activities in the log.…”
Section: Resultsmentioning
confidence: 99%
“…For instance, after a transition system has been constructed from the log, state-based region miner techniques construct a Petri net by folding regions of states into places [4,28]. Typically, statebased region techniques provide rediscoverability guarantees [10], but have problems dealing with parallelism.…”
One of the main challenges in process mining is to discover a process model describing observed behaviour in the best possible manner. Since event logs only contain example behaviour and one cannot assume to have seen all possible process executions, process discovery techniques need to be able to handle incompleteness. In this paper, we study the effects of such incomplete logs on process discovery. We analyse the impact of incompleteness of logs on behavioural relations, which are an abstraction often used by process discovery techniques. We introduce probabilistic behavioural relations that are less sensitive to incompleteness, and exploit these relations to provide a more robust process discovery algorithm. We prove this algorithm to be able to rediscover a model of the original system. Furthermore, we show in experiments that our approach even rediscovers models from incomplete event logs that are much smaller than required by other process discovery algorithms.
“…Several variants of the α algorithm have been proposed [12,13]. Moreover, completely different approaches have been proposed, e.g., the different types of genetic process mining [14,15], techniques based on state-based regions [16,17], and techniques based on language-based regions [18,19]. Another, more recent, approach is inductive process mining where the event log is split recursively [20].…”
Section: Related Workmentioning
confidence: 99%
“…+ -+ --Leemans M., Episode discovery + -n.a. + -+ -+ Van der Aalst, α-algorithm [10] + + -+ + + --Weijters, Heuristics mining [11] + + -+ + + --De Medeiros, Genetic mining [14,15] + + -+ + + + + Solé, State Regions [16,17] + + -+ + + --Bergenthum, Language Regions [18,19] + + -+ + + --Leemans S.J.J., Inductive [20] + + + + + + + - Table 1. Feature comparison of discussed discovery algorithms…”
Abstract. Lion's share of process mining research focuses on the discovery of end-to-end process models describing the characteristic behavior of observed cases. The notion of a process instance (i.e., the case) plays an important role in process mining. Pattern mining techniques (such as frequent itemset mining, association rule learning, sequence mining, and traditional episode mining) do not consider process instances. An episode is a collection of partially ordered events. In this paper, we present a new technique (and corresponding implementation) that discovers frequently occurring episodes in event logs thereby exploiting the fact that events are associated with cases. Hence, the work can be positioned in-between process mining and pattern mining. Episode discovery has its applications in, amongst others, discovering local patterns in complex processes and conformance checking based on partial orders. We also discover episode rules to predict behavior and discover correlated behaviors in processes. We have developed a ProM plug-in that exploits efficient algorithms for the discovery of frequent episodes and episode rules. Experimental results based on real-life event logs demonstrate the feasibility and usefulness of the approach.
“…An alternative generalization was proposed by J. Carmona et al [11]. The application of statebased region algorithms to process mining was studied in [6,9,21]. Algorithms based on regions of languages were presented in [7,14,18] and then applied to process mining [8,24].…”
Abstract. Process mining aims to discover and analyze processes by extracting information from event logs. Process mining discovery algorithms deal with large data sets to learn automatically process models. As more event data become available there is the desire to learn larger and more complex process models. To tackle problems related to the readability of the resulting model and to ensure tractability, various decomposition methods have been proposed. This paper presents a novel decomposition approach for discovering more readable models from event logs on the basis of a priori knowledge about the event log structure: regular and special cases of the process execution are treated separately. The transition system, corresponding to a given event log, is decomposed into a regular part and a specific part. Then one of the known discovery algorithms is applied to both parts, and finally these models are combined into a single process model. It is proven, that the structural and behavioral properties of submodels are inherited by the unified process model. The proposed discovery algorithm is illustrated using a running example.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.