Leveraging path information to generate predictions for parallel business processes

Unuvar, Merve; Lakshmanan, Geetika T.; Doǧanata, Yurdaer N.

doi:10.1007/s10115-015-0842-7

Cited by 32 publications

(19 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results, surpassing or close to the stateof-the-art and with cross-validated precision in excess of 80% on many problems, demonstrate the feasibility and usefulness of this approach. While one can perform prediction by mining a model from event logs, and mining decision rules for each process branch point (Lakshmanan et al, 2015;Unuvar et al, 2016), this has inherent drawbacks. Process mining algorithms trade off different quality criteria, such as fitness, precision, generalizability, and simplicity.…”

Section: Discussionmentioning

confidence: 99%

“…An alternative to RNN are n-gram models, in which a non-recurrent neural network is trained on all fixed-length trace prefixes of length n. The RNN approach has the advantage of allowing prediction from trace prefixes of arbitrary length while also offering better prediction performance (Mikolov et al, 2011). Alternatives to neural networks are probabilistic automatons such as HMM (Lakshmanan et al, 2015;Unuvar et al, 2016) and PFA (Breuker et al, 2016). Section 3.5 showed that the event logs chosen for this study have characteristics that make either of these techniques applicable.…”

Section: Discussionmentioning

confidence: 99%

“…Only five approaches are concerned with predicting the next event (Breuker et al, 2016;Ceci et al, 2014;Lakshmanan et al, 2015;Le et al, 2012;Unuvar et al, 2016), all of which use an explicit model representation such as a state-transition, HMM (hidden Markov models), or PFA (probabilistic finite automatons) model. The MSA approach by Le et al (2012) considers each trace prefix as a state in a state-transition matrix.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Predicting process behaviour using deep learning

Evermann

Rehse

Fettke

2017

Decision Support Systems

323

284

View full text Add to dashboard Cite

Predicting business process behaviour is an important aspect of business process management. Motivated by research in natural language processing, this paper describes an application of deep learning with recurrent neural networks to the problem of predicting the next event in a business process. This is both a novel method in process prediction, which has largely relied on explicit process models, and also a novel application of deep learning methods. The approach is evaluated on two real datasets and our results surpass the state-of-the-art in prediction precision.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Predicting process behaviour using deep learning

Evermann

Rehse

Fettke

2017

Decision Support Systems

323

284

View full text Add to dashboard Cite

show abstract

“…Often events are considered to be multi-dimensional, i.e., there are additional attributes that describe the events in addition to only the business activity. Some of the methods encode the available data as a feature vector, and subsequently apply a classifier to predict the next event [63,76,57]. Other techniques discover a process/sequence model from the control-flow using se-quential pattern mining [25], Markov models [49] or a Probabilistic Finite Automaton [19].…”

Section: Predictive Business Process Monitoringmentioning

confidence: 99%

An interdisciplinary comparison of sequence modeling methods for next-element prediction

2020

View full text Add to dashboard Cite

Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i) in the machine learning field methods such as (hidden) Markov models and recurrent neural networks have been developed and successfully applied to a wide-range of tasks, (ii) in process mining process discovery techniques aim to generate human-interpretable descriptive models, and (iii) in the grammar inference field the focus is on finding descriptive models in the form of formal grammars. Despite their different focuses, these fields share a common goal -learning a model that accurately describes the behavior in the underlying data. Those sequence models are generative, i.e, they can predict what elements are likely to occur after a given unfinished sequence. So far, these fields have developed mainly in isolation from each other and no comparison exists. This paper presents an interdisciplinary experimental evaluation that compares sequence modeling techniques on the task of nextelement prediction on four real-life sequence datasets. The results indicate that machine learning techniques that generally have no aim at interpretability in terms of accuracy outperform techniques from the process mining and grammar inference fields that aim to yield interpretable models.

show abstract

“…Generally, one assumes that each event has a timestamp and belongs to one case (process instance). Process mining enables discovery of a process model from a log, measuring the conformance of a log to a model, enhancement of a process model based on logs, and predictions of process properties [17,18].…”

Section: Bpm-oriented Systemsmentioning

confidence: 99%

From event streams to process models and back: Challenges and opportunities

Soffer

Hinze

Koschmider

et al. 2019

Information Systems

View full text Add to dashboard Cite

The domains of complex event processing (CEP) and business process management (BPM) have different origins but for many aspects draw on similar concepts. While specific combinations of BPM and CEP have attracted research attention, resulting in solutions to specific problems, we attempt to take a broad view at the opportunities and challenges involved. We first illustrate these by a detailed example from the logistics domain. We then propose a mapping of this area into four quadrants -two quadrants drawing from CEP to create or extend process models and two quadrants starting $ This paper is an outcome of discussions and collaborations that were initiated at the Dagstuhl seminar 16341 on "Integrating Process-Oriented and Event-Based Systems" from a process model to address how it can guide CEP. Existing literature is reviewed and specific challenges and opportunities are indicated for each of these quadrants. Based on this mapping, we identify challenges and opportunities that recur across quadrants and can be considered as the core issues of this combination. We suggest that addressing these issues in a generic manner would form a sound basis for future applications and advance this area significantly.

show abstract

Leveraging path information to generate predictions for parallel business processes

Cited by 32 publications

References 15 publications

Predicting process behaviour using deep learning

Predicting process behaviour using deep learning

An interdisciplinary comparison of sequence modeling methods for next-element prediction

From event streams to process models and back: Challenges and opportunities

Contact Info

Product

Resources

About