A Vector-Based Classification Approach for Remaining Time Prediction in Business Processes

In this paper, we deal with one of the current challenges in process mining enhancement: the prediction of remaining times in business processes. Accurate predictions of the remaining time, defined as the required time for an instance process to finish, are critical in many systems for organizations being able to establish a priori requirements, for optimal management of resources or for improving the quality of the services organizations provide. Our approach consists of i) extracting and assessing a number of features on the business logs, that provide a structural characterization of the traces; ii) extending the well-known annotated transition system (ATS) model to include these features; iii) proposing a partitioning strategy for the lists of features associated to each state in the extended ATS; and iv) applying a linear regression technique to each partition for predicting the remaining time of new traces. Extensive experimentation using eight attributes and ten real-life datasets show that the proposed approach outperforms in terms of mean absolute error and accuracy all the other approaches in state of the art, which includes ATS-based, non-ATS based as well as Deep Learning-based approaches.

[1]  Eugenio Cesario,et al.  A Cloud-Based Prediction Framework for Analyzing Business Process Performances , 2016, CD-ARES.

[2]  Marlon Dumas,et al.  Predictive Business Process Monitoring with LSTM Neural Networks , 2016, CAiSE.

[3]  Marcos Sepúlveda,et al.  Process Remaining Time Prediction Using Query Catalogs , 2013, Business Process Management Workshops.

[4]  Boudewijn F. van Dongen,et al.  Cycle Time Prediction: When Will This Case Finally Be Finished? , 2008, OTM Conferences.

[5]  Shiping Chen,et al.  A test-bed for the evaluation of business process prediction techniques , 2011, 7th International Conference on Collaborative Computing: Networking, Applications and Worksharing (CollaborateCom).

[6]  Antonio Ruiz-Cortés,et al.  Predictive Monitoring of Business Processes: A Survey , 2018, IEEE Transactions on Services Computing.

[7]  Wil M. P. van der Aalst,et al.  Beyond Process Mining: From the Past to Present and Future , 2010, CAiSE.

[8]  Rich Caruana,et al.  Greedy Attribute Selection , 1994, ICML.

[9]  Wil M. P. van der Aalst,et al.  Process Mining: Overview and Opportunities , 2012, ACM Trans. Manag. Inf. Syst..

[10]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[11]  Fabrizio Maria Maggi,et al.  Predictive Process Monitoring Methods: Which One Suits Me Best? , 2018, BPM.

[12]  S. M. García,et al.  2014: , 2020, A Party for Lazarus.

[13]  Alessandro Sperduti,et al.  Data-aware remaining time prediction of business process instances , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[14]  Michelangelo Ceci,et al.  Completion Time and Next Activity Prediction of Processes Using Sequential Pattern Mining , 2014, Discovery Science.

[15]  Hoang Nguyen,et al.  White-box prediction of process performance indicators via flow analysis , 2017, ICSSP.

[16]  Fabrizio Maria Maggi,et al.  Intra and Inter-case Features in Predictive Process Monitoring: A Tale of Two Dimensions , 2017, BPM.

[17]  Wil M. P. van der Aalst,et al.  Process Mining , 2016, Springer Berlin Heidelberg.

[18]  Wil M. P. van der Aalst,et al.  Time prediction based on process mining , 2011, Inf. Syst..

[19]  Wil M.P. van der Aalst,et al.  Process Mining Put into Context , 2012, IEEE Internet Computing.

[20]  B. F. van Dongen BPI Challenge 2015 , 2015 .

[21]  Pramodita Sharma 2012 , 2013, Les 25 ans de l’OMC: Une rétrospective en photos.

[22]  Fabrizio Maria Maggi,et al.  Survey and Cross-benchmark Comparison of Remaining Time Prediction Methods in Business Process Monitoring , 2019, ACM Trans. Intell. Syst. Technol..

[23]  Ricardo Seguel,et al.  Process Mining Manifesto , 2011, Business Process Management Workshops.

[24]  Mathias Weske,et al.  Prediction of business process durations using non-Markovian stochastic Petri nets , 2015, Inf. Syst..

[25]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.