Process mining is a field of research that has gained much attention in recent years because of its ability to analyze and improve processes. Indeed, one of the key aspects of process mining is its ability to predict the activities in the future and the time spent on these activities. In this work is proposed the use of Bidirectional LSTM and Multi-Speed Transformer on a recent dataset called BPIC-2020 related to reimbursement process of the University of Technology of Eidenhoven. Results shows that Multi-Speed Transformer is more capable to performs next activity prediction than the Bi-LSTM. Meanwhile, for the elapsed time prediction, the viceversa is true. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Next Activity Prediction and Elapsed Time Prediction on Process Dataset
Dentamaro V.Conceptualization
;Impedovo D.Conceptualization
;Pirlo G.Conceptualization
;Semeraro G.
Conceptualization
2023-01-01
Abstract
Process mining is a field of research that has gained much attention in recent years because of its ability to analyze and improve processes. Indeed, one of the key aspects of process mining is its ability to predict the activities in the future and the time spent on these activities. In this work is proposed the use of Bidirectional LSTM and Multi-Speed Transformer on a recent dataset called BPIC-2020 related to reimbursement process of the University of Technology of Eidenhoven. Results shows that Multi-Speed Transformer is more capable to performs next activity prediction than the Bi-LSTM. Meanwhile, for the elapsed time prediction, the viceversa is true. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
