Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.
Considering Non-sequential
Control Flows for Process
Prediction with Recurrent
Neural Networks
Andreas Metzger, Adrian Neu...
Predictive Process Monitoring
2SEAA 2018, Prague
Monitoring
Prediction
Decision
Time
t t + 
Acceptable/
Planned
Situation...
Process Prediction with RNNs
RNN = Recurrent Neural Network
• Special type of artificial neural network
• Neuron feeds bac...
Considering Non-sequential Control Flows
Cycles
• Incremental prediction
• Direct prediction
Parallel branches
• No path: ...
Experiment
Cargo 2000 Data Set
• 3,942 process instances
• 56,082 process steps
• Challenging: Parallel branches include
s...
-0,05
0,05
0,15
0,25
0,35
0,45
0,55
0,65
0% 10% 20% 30% 40% 50% 60% 70% 80% 90%
Results
SEAA 2018, Prague 6
Incremental Pr...
Conclusion and Outlook
• Deep learning promising technique for predictive business
process monitoring
• Facilitates proact...
Thank you!
…the EFRE co-financed operational
program NRW.Ziel2
http://www.lofip.de
…the EU’s Horizon 2020 research and inn...
Nächste SlideShare
Wird geladen in …5
×

Considering Non-sequential Control Flows for Process Prediction with Recurrent Neural Networks

34 Aufrufe

Veröffentlicht am

Predictive business process monitoring aims to
predict how an ongoing process instance will unfold up to
its completion, thereby facilitating proactively responding to
anticipated problems. Recurrent Neural Networks (RNNs), a
special form of deep learning techniques, gain interest as a
prediction technique in BPM. However, non-sequential control
flows may make the prediction task more difficult, because
RNNs were conceived for learning and predicting sequences of
data. Based on an industrial dataset, we provide experimental
results comparing different alternatives for considering non-
sequential control flows. In particular, we consider cycles and
parallelism for business process prediction with RNNs.

Veröffentlicht in: Daten & Analysen
  • Als Erste(r) kommentieren

  • Gehören Sie zu den Ersten, denen das gefällt!

Considering Non-sequential Control Flows for Process Prediction with Recurrent Neural Networks

  1. 1. Considering Non-sequential Control Flows for Process Prediction with Recurrent Neural Networks Andreas Metzger, Adrian Neubauer
  2. 2. Predictive Process Monitoring 2SEAA 2018, Prague Monitoring Prediction Decision Time t t +  Acceptable/ Planned Situations Violation Proactive Adaptation No Violation  Prediction accuracy is essential • Missing a true violation  No adaptation  Violation not prevented • Predicting a false violation  Unnecessary adaptation e.g., completion of transport process by given deadline
  3. 3. Process Prediction with RNNs RNN = Recurrent Neural Network • Special type of artificial neural network • Neuron feeds back information into itself Advantages of RNNs • High accuracy in general • Can handle arbitrary number of process steps • One prediction model sufficient to make prediction at any point in time (“checkpoint”) Problem • RNNs devised for natural language processing (linear sequences of text) • Non-sequential control flow (order of process steps) may make RNN prediction more difficult  How to consider non-sequential control flows? 3
  4. 4. Considering Non-sequential Control Flows Cycles • Incremental prediction • Direct prediction Parallel branches • No path: No encoding of parallel branches • Path: Parallel branch encoded as attribute of process step • Slice: Encoding of steps running in parallel 4 No path A E F Path A1 E2 . F2 Slice AE BE BF Parallel Branch 1 No path: Path: Slice: A B E F Parallel Branch 2 Accumulation of prediction error B A A A
  5. 5. Experiment Cargo 2000 Data Set • 3,942 process instances • 56,082 process steps • Challenging: Parallel branches include same types of process steps Environment / Tooling • Adaptation of LSTM-Realization of RNN [Tax et al. @ CAiSE 2017] • Cloud environment for training: 15 physical machines, dockerized • Ca. 3 hours training / model Accuracy Metric: MCC • Robust against class imbalances • More challenging to score high on 5
  6. 6. -0,05 0,05 0,15 0,25 0,35 0,45 0,55 0,65 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% Results SEAA 2018, Prague 6 Incremental Prediction Direct Prediction -0,05 0,05 0,15 0,25 0,35 0,45 0,55 0,65 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% MCC No path Path Slice No path Path Slice Accuracy [MCC] Checkpoint MLP Direct Prediction 6.3% (avg) better than Incremental But: Flip after 50% mark! 0,24750 -36% RNN 36% better than “traditional” Neural Network Impact of parallel encoding very small: 1.4% (avg)
  7. 7. Conclusion and Outlook • Deep learning promising technique for predictive business process monitoring • Facilitates proactive business process management based on accurate predictions • Improvement of accuracy when explicitly considering non- sequential control flows • Cycles: +6.3 % • Parallel branches: +1.4% • Future work • Further empirical evidence (port logistics, e-commerce, …) • Measure impact of control flow structure and complexity on accuracy SEAA 2018, Prague 7
  8. 8. Thank you! …the EFRE co-financed operational program NRW.Ziel2 http://www.lofip.de …the EU’s Horizon 2020 research and innovation programme under Objective ICT-15 ‘Big Data PPP: Large Scale Pilot Actions ‘ http://www.transformingtransport.eu Research leading to these results has received funding from… SEAA 2018, Prague 8

×