Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring

Nguyen, An; Chatterjee, Srijeet; Weinzierl, Sven; Schwinn, Leo; Matzner, Martin; Eskofier, Bjoern M.

doi:10.1007/978-3-030-72693-5_9

Cited by 17 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…tax [15] et al were inspired by the above methods and made the prediction model perform better by multi-task learning. nguyen [16] et al proposed a time-aware T-LSTM method, while introducing a cost-sensitive learning approach to address the uneven distribution of event log activities, with a significant improvement in prediction accuracy over other methods.Lin [17] et al proposed an encoder-decoder framework, MM-Pred, by separately encoding attributes such as event name, timestamp, and event status as inputs to the model, which recoded the event internal dependencies to establish a connection and use LSTM networks to complete the prediction. jalayer [18] et al built on the above by introducing a hierarchical attention mechanism to assign different weights to each attribute and combined with BiLSTM networks to further improve the prediction accuracy of the model.…”

Section: Related Workmentioning

confidence: 99%

GCN-ONLSTM: Process Next Event Prediction Method based on Spatio-Temporal Feature Fusion

Lele¹,

Liu²,

Chongguang³

2023

International Journal of Science and Engineering Applications

View full text Add to dashboard Cite

The task of predicting the next event of a process is the focus of research in the field of predictive process monitoring. Most of the existing methods to achieve this task only process the event log trace as a one-dimensional sequence or regular two-dimensional image data, without considering the simultaneous internal synchronization of the event log. It contains temporal and spatial feature information. In addition, existing studiesignore that trace data is a non-Euclidean structure with topological relationships. In order to solve the above problems and further improve the accuracy of model prediction, this paper constructs a GCN-ONLSTM network that fuses temporal and spatial dimension features, constructs the spatial relationship between events through a two-layer graph convolution network, and improves the feature expression ability of data. And combined with ONLSTM (Ordered Neurons LSTM) network to process the hierarchical structure of trace sequence, to further solve the long-term dependency problem. The ablation experiments and comparison experiments are carried out through 6 BPI public event log data. The results show that the proposed method has significantly improved prediction accuracy in each event log compared with other existing deep learning methods, and the highest is higher than the traditional LSTM (Long Short-term Memory) increased by 8.63%, it can be considered that this method has better performance for the next event prediction task of the process.

show abstract

Section: Related Workmentioning

confidence: 99%

GCN-ONLSTM: Process Next Event Prediction Method based on Spatio-Temporal Feature Fusion

Lele¹,

Liu²,

Chongguang³

2023

International Journal of Science and Engineering Applications

View full text Add to dashboard Cite

show abstract

“…The LSTM network model has proven to be particularly effective for predictive monitoring [9,23], since the recurrent architecture can natively support sequences of data of arbitrary length. It allows performing trace prediction while employing a fixed-length event abstraction, which can be based on control-flow alone [9,23], data-aware [24], time-aware [25], text-aware [26], or model-aware [20]. Additionally, rather than leveraging control-flow information for prediction, some recent research aims to use predictive monitoring to reconstruct missing control-flow attributes such as labels [27] or case identifiers [28,29].…”

Section: Predictive Process Monitoringmentioning

confidence: 99%

Event Log Sampling for Predictive Monitoring

Sani

Vazifehdoostirani

Park

et al. 2022

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. This paper proposes an instance selection procedure that allows sampling training process instances for prediction models. We show that our sampling method allows for a significant increase of training speed for next activity prediction methods while maintaining reliable levels of prediction accuracy.

show abstract

“…The notion of distance used on these words used is usually either Hamming distance or Levenshtein's edit distance. It is natural to want to study explicitly timed systems as by considering events along with their timestamps when mining processes, we can study the minimum delay between two events, or the maximum duration the system takes to converge upon a state, or check deadlines, all of which are highly relevant in real world applications [5] [6] [7]. In addition, one may want to predict the timestamps of processes [8].…”

Section: B Time-aware Processesmentioning

confidence: 99%

Timed Alignments

Chatain

Rino

2022

2022 4th International Conference on Process Mining (ICPM)

View full text Add to dashboard Cite

The subject of this paper is to study conformance checking for timed models, that is, process models that consider both the sequence of events in a process as well as the timestamps at which each event is recorded. Time-aware process mining is a growing subfield of research, and as tools that seek to discover timing related properties in processes develop, so does the need for conformance checking techniques that can tackle time constraints and provide insightful quality measures for time-aware process models. In particular, one of the most useful conformance artefacts is the alignment, that is, finding the minimal changes necessary to correct a new observation to conform to a process model. In this paper, we set our problem of timed alignment and solve two cases each corresponding to a different metric over time processes. For the first, we have an algorithm whose time complexity is linear both in the size of the observed trace and the process model, while for the second we have a quadratic time algorithm for linear process models.

show abstract

Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring

Cited by 17 publications

References 16 publications

GCN-ONLSTM: Process Next Event Prediction Method based on Spatio-Temporal Feature Fusion

GCN-ONLSTM: Process Next Event Prediction Method based on Spatio-Temporal Feature Fusion

Event Log Sampling for Predictive Monitoring

Timed Alignments

Contact Info

Product

Resources

About