2015
DOI: 10.1007/s10115-015-0842-7
|View full text |Cite
|
Sign up to set email alerts
|

Leveraging path information to generate predictions for parallel business processes

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
19
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 32 publications
(19 citation statements)
references
References 15 publications
0
19
0
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%
See 2 more Smart Citations
“…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%
See 1 more Smart Citation
“…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%
“…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%