Predicting the Next Process Event Using Convolutional Neural Networks

Al-Jebrni, Abdulrhman H.; Cai, Hongming; Jiang, Lihong

doi:10.1109/pic.2018.8706282

Cited by 16 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, next event prediction algorithms are increasingly based on deep learning due the superior performance of neural networks. A body of literature has been proposed using multiple different deep learning architectures for predictive process analytics, such as recurrent neural networks [14], [4], convolutional neural networks [15], [16], [17], stacked autoencoders [18], multi-view deep learning architectures [3], graph neural networks [19], and generative adversarial networks [5]. These deep learning models usually outperform probabilistic methods but are currently lacking interpretability issues since the processes are modeled implicitly using event log data.…”

Section: Related Workmentioning

confidence: 99%

Masking Neural Networks Using Reachability Graphs to Predict Process Events

Theis,

Darabi

2021

Preprint

View full text Add to dashboard Cite

Decay Replay Mining is a deep learning method that utilizes process model notations to predict the next event. However, this method does not intertwine the neural network with the structure of the process model to its full extent. This paper proposes an approach to further interlock the process model of Decay Replay Mining with its neural network for next event prediction. The approach uses a masking layer which is initialized based on the reachability graph of the process model. Additionally, modifications to the neural network architecture are proposed to increase the predictive performance. Experimental results demonstrate the value of the approach and underscore the importance of discovering precise and generalized process models.

show abstract

Section: Related Workmentioning

confidence: 99%

Masking Neural Networks Using Reachability Graphs to Predict Process Events

Theis,

Darabi

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, Al-Jebrni et al [20] present a DNN architecture with an embedding layer followed by five convolutional blocks for the next activity prediction.…”

Section: Deep-learning-based Pbpm Techniques For Next Activity Predic...mentioning

confidence: 99%

“…They embed activities and consider the time difference between the current and the first event in a process instance. We add the CNN architecture of Al-Jebrni et al [20] to our evaluation since the authors report the highest predictive quality. Again, we remove the embedding layer from the DNN architecture to be more flexible regarding the attribute encoding.…”

Section: Deep-learning-based Pbpm Techniques For Next Activity Predic...mentioning

confidence: 99%

“…These architectural types are: (1) multi-layer perceptron (MLP) [17,18], (2) recurrent neural network (RNN) (e.g. [15,19,11]) and (3) convolutional neural network (CNN) [20,21,22].…”

Section: Introductionmentioning

confidence: 99%

“…For that, we empirically evaluate the predictive quality for an instance of each of the three applied DNN architecture types (MLP by Theis and Darabi [18], long short-term neural network (LSTM) by Camargo et al [27] and CNN by Al-Jebrni et al [20]). Additionally, we include five proven encoding techniques from the ML literature (binary, ordinal, onehot, hash and word2vec) in our evaluation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An empirical comparison of deep-neural-network architectures for next activity prediction using context-enriched process event logs

Weinzierl¹,

Zilker²,

Brunk³

et al. 2020

Preprint

View full text Add to dashboard Cite

Researchers have proposed a variety of predictive business process monitoring (PBPM) techniques aiming to predict future process behaviour during the process execution. Especially, techniques for the next activity prediction anticipate great potential in improving operational business processes. To gain more accurate predictions, a plethora of these techniques rely on deep neural networks (DNNs) and consider information about the context, in which the process is running. However, an in-depth comparison of such techniques is missing in the PBPM literature, which prevents researchers and practitioners from selecting the best solution for a given event log. To remedy this problem, we empirically evaluate the predictive quality of three promising DNN architectures, combined with five proven encoding techniques and based on five context-enriched real-life event logs. We provide four findings that can support researchers and practitioners in designing novel PBPM techniques for predicting the next activities.

show abstract