Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances
| Autor: | Yelita Anggiane Iskandar, Hyerim Bae, Yulim Choi, Taufik Nur Adi, Nur Ahmad Wahid |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Technology
QH301-705.5 Process (engineering) Computer science Business process QC1-999 remaining time prediction convolutional neural network Context (language use) Machine learning computer.software_genre Convolutional neural network Information system General Materials Science Biology (General) QD1-999 Instrumentation Fluid Flow and Transfer Processes business.industry Event (computing) Physics Process Chemistry and Technology Deep learning General Engineering deep learning Engineering (General). Civil engineering (General) Perceptron Computer Science Applications predictive business process monitoring Chemistry Artificial intelligence TA1-2040 embedding layer business computer |
| Zdroj: | Applied Sciences Volume 11 Issue 21 Applied Sciences, Vol 11, Iss 9848, p 9848 (2021) |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app11219848 |
| Popis: | Event logs generated by Process-Aware Information Systems (PAIS) provide many opportunities for analysis that are expected to help organizations optimize their business processes. The ability to monitor business processes proactively can allow an organization to achieve, maintain or enhance competitiveness in the market. Predictive Business Process Monitoring (PBPM) can provide measures such as the prediction of the remaining time of an ongoing process instance (case) by taking past activities in running process instances into account, as based on the event logs of previously completed process instances. With the prediction provided, we expect that organizations can respond quickly to deviations from the desired process. In the context of the growing popularity of deep learning and the need to utilize heterogeneous representation of data in this study, we derived a new deep-learning approach that utilizes two types of data representation based on a parallel-structure model, which consists of a convolutional neural network (CNN) and a multi-layer perceptron (MLP) with an embedding layer, to predict the remaining time. Conducting experiments with real-world datasets, we compared our proposed method against the existing deep-learning approach to confirm its utility for the provision of more precise prediction (as indicated by error metrics) relative to the baseline method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|