Predição de tempo restante para conclusão de processos de negócio utilizando aprendizado profundo
Business process analysis belongs to process mining study area that covers the predictive monitoring process and aim to do predictions over both individuals process like: what the next process instance will be executed when provide past events, the remaining time to process instance conclusion when...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Estado: | Versión publicada |
| Fecha de publicación: | 2023 |
| País: | Brasil |
| Institución: | Universidade Federal do Ceará (UFC) |
| Repositorio: | Repositório Institucional da Universidade Federal do Ceará (UFC) |
| Idioma: | portugués |
| OAI Identifier: | oai:repositorio.ufc.br:riufc/75231 |
| Acceso en línea: | http://repositorio.ufc.br/handle/riufc/75231 |
| Access Level: | acceso abierto |
| Palabra clave: | Processo de negócio Predição de tempo restante Aprendizagem profunda |
| Sumario: | Business process analysis belongs to process mining study area that covers the predictive monitoring process and aim to do predictions over both individuals process like: what the next process instance will be executed when provide past events, the remaining time to process instance conclusion when it applies in general process models that is not necessarily includes a business focus. This work aims to predict the remaining time to complete a business process instance using deep learning models. Efficiently predicting the remaining time to complete a process instance contributes to preventing uncertain waits, discovering bottlenecks in processes, and assist alert systems. This paper proposes new architectures of deep learning with recurrent networks to predict the remaining time to conclusion a business process, which surpass state-of-the-art solutions. The architectures used are validated with two sets of public data and another three private one, facilitating the reproducibility of the experiments. |
|---|