Predictive Business Process Monitoring with LSTM Neural Networks

@article{Tax2017PredictiveBP,
  title={Predictive Business Process Monitoring with LSTM Neural Networks},
  author={Niek Tax and Ilya Verenich and Marcello La Rosa and Marlon Dumas},
  journal={ArXiv},
  year={2017},
  volume={abs/1612.02130}
}
Predictive business process monitoring methods exploit logs of completed cases of a process in order to make predictions about running cases thereof. Existing methods in this space are tailor-made for specific prediction tasks. Moreover, their relative accuracy is highly sensitive to the dataset at hand, thus requiring users to engage in trial-and-error and tuning when applying them in a specific setting. This paper investigates Long Short-Term Memory (LSTM) neural networks as an approach to… 
Learning Accurate LSTM Models of Business Processes
TLDR
An approach to train recurrent neural networks with Long-Short-Term Memory (LSTM) architecture in order to predict sequences of next events, their timestamp, and their associated resource pools is proposed.
Attention Mechanism in Predictive Business Process Monitoring
TLDR
A novel approach inspired by the notion of attention mechanism, utilized in Natural Language Processing and, particularly, in Neural Machine Translation is presented, which uses all hidden states to accurately predict future behavior and the outcome of individual activities.
ProcessTransformer: Predictive Business Process Monitoring with Transformer Network
TLDR
It is demonstrated that the transformer-based model outperforms several baselines of prior techniques by obtaining on average above 80% accuracy for the task of predicting the next activity and also perform competitively, compared to baselines, for the tasks of predicting event time and remaining time of a running case.
Explainable predictive business process monitoring using gated graph neural networks
TLDR
This work is the first to use gated graph neural networks (GGNNs) to make decisions more explainable, and it’s also GGNN's first application to PBPM.
Deep Learning Process Prediction with Discrete and Continuous Data Features
TLDR
It is shown how prediction accuracy can significantly be improved by incorporating event data attributes, and this extension of conventional algorithms is regarded as a substantial contribution to the field of activity prediction.
Exploring the effect of context information on deep learning business process predictions
TLDR
First, a context-sensitive prediction capability can improve the predictive quality of an LSTM-based technique, and second, the added value of context information to the quality of predicting the next activity varies in the course of a running process instance.
LSTM networks for data-aware remaining time prediction of business process instances
TLDR
This paper proposes an approach based on deep Recurrent Neural Networks (specifically LSTMs) that is able to exploit arbitrary information associated to single events in order to produce an as-accurate-as-possible prediction of the completion time of running instances.
Outcome-Oriented Predictive Process Monitoring with Attention-Based Bidirectional LSTM Neural Networks
TLDR
This work proposes an effective approach based on deep learning techniques, called Att-Bi-LSTM, which is combined with the bidirectional long short-term memory network and the attention-mechanism, which can capture and optimize the features that have a decisive effect on the outcome for a completed case so as to construct a predictive model with good performance.
Predicting Activities in Business Processes with LSTM Recurrent Neural Networks
TLDR
This article shows that LSTM networks can also be used for the prediction of execution of cases in the context of an event log that originates from the IoT and Industry 4.0 domain.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 32 REFERENCES
Predictive Business Process Monitoring Framework with Hyperparameter Optimization
TLDR
This paper presents a predictive process monitoring framework armed with a hyperparameter optimization method to select a suitable framework instance for a given dataset.
Discovering Context-Aware Models for Predicting Business Process Performances
TLDR
This work proposes an ad-hoc predictive clustering approach, where different context-related execution scenarios are discovered and modeled accurately via distinct state-aware performance predictors, and obtains a readable predictive model, which can make performance forecasts for any new running process case, by using the predictor of the cluster it is estimated to belong to.
Time and activity sequence prediction of business process instances
TLDR
A method, assuming process stationarity, is proposed which achieves state-of-the-art performances and two other methods which are able to make predictions even with non-stationary processes are described, able to predict the full sequence of activities that a running case is going to take.
A Deep Learning Approach for Predicting Process Behaviour at Runtime
TLDR
This paper describes an initial application of deep learning with recurrent neural networks to the problem of predicting the next process event, which is both a novel method in process prediction, and also a novel application for deep learning methods.
Clustering-Based Predictive Process Monitoring
TLDR
This paper proposes a predictive process monitoring framework for estimating the probability that a given predicate will be fulfilled upon completion of a running case and takes into account both the sequence of events observed in the current trace, as well as data attributes associated to these events.
Comparing and Combining Predictive Business Process Monitoring Techniques
TLDR
This work empirically analyzes and compares three main classes of predictive monitoring techniques, which are based on machine learning, constraint satisfaction, and Quality-of-Service (QoS) aggregation, and indicates that certain combinations of techniques may outperform individual techniques with respect to specific accuracy indicators.
Process Mining to Forecast the Future of Running Cases
TLDR
This paper details a process mining approach, which uses predictive clustering to equip an execution scenario with a prediction model that accounts for recent events of running cases to predict the characteristics of future events.
Comprehensible Predictive Models for Business Processes
TLDR
A new predictive modeling technique based on weaker biases is designed, fitting a probabilistic model to a data set of past behavior makes it possible to predict how currently running process instances will behave in the future.
A markov prediction model for data-driven semi-structured business processes
TLDR
Results indicate that an instance-specific probabilistic process model (PPM) whose transition probabilities are customized to the semi-structured business process instance it represents provides more accurate predictions than other methods such as conditional probability.
Complex Symbolic Sequence Encodings for Predictive Monitoring of Business Processes
TLDR
Different feature encodings of complex symbolic sequences of events each carrying a data payload are outlined and compared their predictive accuracy on real-life business process event logs.
...
1
2
3
4
...