Time and activity sequence prediction of business process instances

Mirko Polato, Alessandro Sperduti, Andrea Burattin, Massimiliano de Leoni

Research output: Contribution to journalArticleAcademicpeer-review

13 Citations (Scopus)

Abstract

The ability to know in advance the trend of running process instances, with respect to different features, such as the expected completion time, would allow business managers to timely counteract to undesired situations, in order to prevent losses. Therefore, the ability to accurately predict future features of running business process instances would be a very helpful aid when managing processes, especially under service level agreement constraints. However, making such accurate forecasts is not easy: many factors may influence the predicted features. Many approaches have been proposed to cope with this problem but, generally, they assume that the underlying process is stationary. However, in real cases this assumption is not always true. In this work we present new methods for predicting the remaining time of running cases. In particular we propose a method, assuming process stationarity, which achieves state-of-the-art performances and two other methods which are able to make predictions even with non-stationary processes. We also describe an approach able to predict the full sequence of activities that a running case is going to take. All these methods are extensively evaluated on different real case studies.

Original languageEnglish
Pages (from-to)1005–1031
Number of pages27
JournalComputing
Volume100
Issue number9
DOIs
Publication statusPublished - 1 Sep 2018

Fingerprint

Business Process
Prediction
Industry
Managers
Predict
Nonstationary Processes
Service Level Agreement
Stationarity
Completion Time
Forecast

Keywords

  • Machine learning
  • Prediction
  • Process mining
  • Remaining time

Cite this

Polato, Mirko ; Sperduti, Alessandro ; Burattin, Andrea ; de Leoni, Massimiliano . / Time and activity sequence prediction of business process instances. In: Computing. 2018 ; Vol. 100, No. 9. pp. 1005–1031.
@article{d1ee3f97deeb40fa91ed6779ffdf21ad,
title = "Time and activity sequence prediction of business process instances",
abstract = "The ability to know in advance the trend of running process instances, with respect to different features, such as the expected completion time, would allow business managers to timely counteract to undesired situations, in order to prevent losses. Therefore, the ability to accurately predict future features of running business process instances would be a very helpful aid when managing processes, especially under service level agreement constraints. However, making such accurate forecasts is not easy: many factors may influence the predicted features. Many approaches have been proposed to cope with this problem but, generally, they assume that the underlying process is stationary. However, in real cases this assumption is not always true. In this work we present new methods for predicting the remaining time of running cases. In particular we propose a method, assuming process stationarity, which achieves state-of-the-art performances and two other methods which are able to make predictions even with non-stationary processes. We also describe an approach able to predict the full sequence of activities that a running case is going to take. All these methods are extensively evaluated on different real case studies.",
keywords = "Machine learning, Prediction, Process mining, Remaining time",
author = "Mirko Polato and Alessandro Sperduti and Andrea Burattin and {de Leoni}, Massimiliano",
year = "2018",
month = "9",
day = "1",
doi = "10.1007/s00607-018-0593-x",
language = "English",
volume = "100",
pages = "1005–1031",
journal = "Computing",
issn = "0010-485X",
publisher = "Springer",
number = "9",

}

Time and activity sequence prediction of business process instances. / Polato, Mirko; Sperduti, Alessandro; Burattin, Andrea; de Leoni, Massimiliano .

In: Computing, Vol. 100, No. 9, 01.09.2018, p. 1005–1031.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Time and activity sequence prediction of business process instances

AU - Polato, Mirko

AU - Sperduti, Alessandro

AU - Burattin, Andrea

AU - de Leoni, Massimiliano

PY - 2018/9/1

Y1 - 2018/9/1

N2 - The ability to know in advance the trend of running process instances, with respect to different features, such as the expected completion time, would allow business managers to timely counteract to undesired situations, in order to prevent losses. Therefore, the ability to accurately predict future features of running business process instances would be a very helpful aid when managing processes, especially under service level agreement constraints. However, making such accurate forecasts is not easy: many factors may influence the predicted features. Many approaches have been proposed to cope with this problem but, generally, they assume that the underlying process is stationary. However, in real cases this assumption is not always true. In this work we present new methods for predicting the remaining time of running cases. In particular we propose a method, assuming process stationarity, which achieves state-of-the-art performances and two other methods which are able to make predictions even with non-stationary processes. We also describe an approach able to predict the full sequence of activities that a running case is going to take. All these methods are extensively evaluated on different real case studies.

AB - The ability to know in advance the trend of running process instances, with respect to different features, such as the expected completion time, would allow business managers to timely counteract to undesired situations, in order to prevent losses. Therefore, the ability to accurately predict future features of running business process instances would be a very helpful aid when managing processes, especially under service level agreement constraints. However, making such accurate forecasts is not easy: many factors may influence the predicted features. Many approaches have been proposed to cope with this problem but, generally, they assume that the underlying process is stationary. However, in real cases this assumption is not always true. In this work we present new methods for predicting the remaining time of running cases. In particular we propose a method, assuming process stationarity, which achieves state-of-the-art performances and two other methods which are able to make predictions even with non-stationary processes. We also describe an approach able to predict the full sequence of activities that a running case is going to take. All these methods are extensively evaluated on different real case studies.

KW - Machine learning

KW - Prediction

KW - Process mining

KW - Remaining time

UR - http://www.scopus.com/inward/record.url?scp=85042069635&partnerID=8YFLogxK

U2 - 10.1007/s00607-018-0593-x

DO - 10.1007/s00607-018-0593-x

M3 - Article

AN - SCOPUS:85042069635

VL - 100

SP - 1005

EP - 1031

JO - Computing

JF - Computing

SN - 0010-485X

IS - 9

ER -