2018 · 18 citations · 13 references
ComputingComputer ScienceInformation SystemsForecastingMachine LearningPredictive AnalyticsDeep LearningRepresentation LearningTime Series ForecastingTime Series PredictionConvolutional Neural NetworksDeep Learning For ForecastingDeep Learning-based ForecastingLong Short-term Memory NetworksRecurrent Neural Network ForecastingRecurrent Neural Networks
Adding the feature of business process event prediction to information systems increases its productivity in the long run, enhances the quality of the taken decisions, and eliminates inconsistencies. Inspired by the previous works of employing deep learning approaches to predicting the next process event based on files of logged events, we propose the use of one-dimensional convolutional neural networks (1D CNN) to address the same problem. In the proposed approach we used a five-layer 1D CNN method to predict the next process event based on the previous instances. This paper compared the proposed approach with other approaches that used recurrent neural networks (RNN) with Long Short-Term Memory (LSTM) neural networks, and others on eight datasets. The proposed approach outperformed all the previous studies of the state-of-the-art in this domain on all the provided datasets.
13
Recurrent Neural Network Regularization
Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals · arXiv (Cornell University) · 2014 · 2.3K citations · Full text
Generating Text with Recurrent Neural Networks
Ilya Sutskever, James Martens, Geoffrey E. Hinton · 2011 · 1.2K citations