Decay Replay Mining to Predict Next Process Events
In complex processes, various events can happen in different sequences. The prediction of the next event given an a-priori process state is of importance in such processes. Recent methods have proposed deep learning techniques such as recurrent neural networks, developed on raw event logs, to predic...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8811455/ |
| _version_ | 1818855468141903872 |
|---|---|
| author | Julian Theis Houshang Darabi |
| author_facet | Julian Theis Houshang Darabi |
| author_sort | Julian Theis |
| collection | DOAJ |
| description | In complex processes, various events can happen in different sequences. The prediction of the next event given an a-priori process state is of importance in such processes. Recent methods have proposed deep learning techniques such as recurrent neural networks, developed on raw event logs, to predict the next event from a process state. However, such deep learning models by themselves lack a clear representation of the process states. At the same time, recent methods have neglected the time feature of event instances. In this paper, we take advantage of Petri nets as a powerful tool in modeling complex process behaviors considering time as an elemental variable. We propose an approach which starts from a Petri net process model constructed by a process mining algorithm. We enhance the Petri net model with time decay functions to create continuous process state samples. Finally, we use these samples in combination with discrete token movement counters and Petri net markings to train a deep learning model that predicts the next event. We demonstrate significant performance improvements and outperform the state-of-the-art methods on nine real-world benchmark event logs. |
| first_indexed | 2024-12-19T08:09:05Z |
| format | Article |
| id | doaj.art-8b14ce2b42be44bbb02ec7161c2b5b26 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T08:09:05Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8b14ce2b42be44bbb02ec7161c2b5b262022-12-21T20:29:40ZengIEEEIEEE Access2169-35362019-01-01711978711980310.1109/ACCESS.2019.29370858811455Decay Replay Mining to Predict Next Process EventsJulian Theis0https://orcid.org/0000-0003-0954-0938Houshang Darabi1https://orcid.org/0000-0001-7881-6542Mechanical and Industrial Engineering Department, University of Illinois at Chicago, Chicago, IL, USAMechanical and Industrial Engineering Department, University of Illinois at Chicago, Chicago, IL, USAIn complex processes, various events can happen in different sequences. The prediction of the next event given an a-priori process state is of importance in such processes. Recent methods have proposed deep learning techniques such as recurrent neural networks, developed on raw event logs, to predict the next event from a process state. However, such deep learning models by themselves lack a clear representation of the process states. At the same time, recent methods have neglected the time feature of event instances. In this paper, we take advantage of Petri nets as a powerful tool in modeling complex process behaviors considering time as an elemental variable. We propose an approach which starts from a Petri net process model constructed by a process mining algorithm. We enhance the Petri net model with time decay functions to create continuous process state samples. Finally, we use these samples in combination with discrete token movement counters and Petri net markings to train a deep learning model that predicts the next event. We demonstrate significant performance improvements and outperform the state-of-the-art methods on nine real-world benchmark event logs.https://ieeexplore.ieee.org/document/8811455/Business process intelligencedecay functionsdeep learningpetri netsneural networksoperational runtime support |
| spellingShingle | Julian Theis Houshang Darabi Decay Replay Mining to Predict Next Process Events IEEE Access Business process intelligence decay functions deep learning petri nets neural networks operational runtime support |
| title | Decay Replay Mining to Predict Next Process Events |
| title_full | Decay Replay Mining to Predict Next Process Events |
| title_fullStr | Decay Replay Mining to Predict Next Process Events |
| title_full_unstemmed | Decay Replay Mining to Predict Next Process Events |
| title_short | Decay Replay Mining to Predict Next Process Events |
| title_sort | decay replay mining to predict next process events |
| topic | Business process intelligence decay functions deep learning petri nets neural networks operational runtime support |
| url | https://ieeexplore.ieee.org/document/8811455/ |
| work_keys_str_mv | AT juliantheis decayreplayminingtopredictnextprocessevents AT houshangdarabi decayreplayminingtopredictnextprocessevents |