Explainable Predictive Process Monitoring

Galanti, Riccardo; Coma-Puig, Bernat; Leoni, Massimiliano de; Carmona, Josep; Navarin, Nicolò

doi:10.1109/icpm49681.2020.00012

Cited by 55 publications

(39 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…rework): Pending Request for Acquittance of Heirs, Back-Office Adjust Requested and Autorization Required. Space limitation prevents us from showing here all of three: here we focus on activity Back-Office Adjust Requested, while the other two are in the appendix complementing the paper [6]. The learnt LSTM model was characterized by an F1 score of 0.65, an Area Under the Receiver Operating Charateristics (AUROC) of 0.86, and an Area under Precision/Recall curve (APR) of 0.69.…”

Section: Results On Prediction Of Activity Occurrencementioning

confidence: 99%

See 1 more Smart Citation

Explainable Predictive Process Monitoring

Galanti¹,

Coma-Puig²,

Leoni³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Predictive Business Process Monitoring is becoming an essential aid for organizations, providing online operational support of their processes. This paper tackles the fundamental problem of equipping predictive business process monitoring with explanation capabilities, so that not only the what but also the why is reported when predicting generic KPIs like remaining time, or activity execution. We use the game theory of Shapley Values to obtain robust explanations of the predictions. The approach has been implemented and tested on real-life benchmarks, showing for the first time how explanations can be given in the field of predictive business process monitoring.

show abstract

Section: Results On Prediction Of Activity Occurrencementioning

confidence: 99%

“…However, we also conducted several additional experiments with publicly-available event logs, previously used as predictive process-monitoring benchmarks. Space limitation prevent us from reporting on them, which are however discussed in the appendix that complements this paper [6].…”

Section: Implementation and Experimentsmentioning

confidence: 99%

Explainable Predictive Process Monitoring

Galanti¹,

Coma-Puig²,

Leoni³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, the authors also illustrate the potential use of explainable AI in process prediction through experimentation in the DFKI-Smart-Lego-Factory prototype. Galanti et al [166] also proposed an explainable AL solution for process monitoring in the Industry 4.0 setup. The proposed solution is evaluated on real industry benchmark datasets.…”

Section: B Explainability and Intrepretabilitymentioning

confidence: 99%

The Duo of Artificial Intelligence and Big Data for Industry 4.0: Review of Applications, Techniques, Challenges, and Future Research Directions

Jagatheesaperumal¹,

Rahouti²,

Ahmad³

et al. 2021

Preprint

View full text Add to dashboard Cite

The increasing need for economic, safe, and sustainable smart manufacturing combined with novel technological enablers, has paved the way for Artificial Intelligence (AI) and Big Data in support of smart manufacturing. This implies a substantial integration of AI, Industrial Internet of Things (IIoT), Robotics, Big data, Blockchain, 5G communications, in support of smart manufacturing and the dynamical processes in modern industries. In this paper, we provide a comprehensive overview of different aspects of AI and Big Data in Industry 4.0 with a particular focus on key applications, techniques, the concepts involved, key enabling technologies, challenges, and research perspective towards deployment of Industry 5.0. In detail, we highlight and analyze how the duo of AI and Big Data is helping in different applications of Industry 4.0. We also highlight key challenges in a successful deployment of AI and Big Data methods in smart industries with a particular emphasis on data-related issues, such as availability, bias, auditing, management, interpretability, communication, and different adversarial attacks and security issues. In a nutshell, we have explored the significance of AI and Big data towards Industry 4.0 applications through panoramic reviews and discussions. We believe, this work will provide a baseline for future research in the domain.

show abstract

“…In our system, we use the Tree Explainer, the specific method to extract the Shapley Values from Tree Models . Some examples of the use Shapley Values are; , an example of using the Shapley Values to prevent hypoxaemia during surgery; Galanti et al (2020), an example of using Shapley Values to explain LSTM models in predictive process monitoring (business process management); or Posada-Quintero et al (2020), a social science work in which the Shapley Values are used to understand the risk factors associated with teacher burnout.…”

Section: Related Work In Robustness and Explainabilitymentioning

confidence: 99%

Non-technical losses detection in energy consumption focusing on energy recovery and explainability

Coma-Puig

Carmona

2021

Mach Learn

Self Cite

View full text Add to dashboard Cite

Non-technical losses (NTL) is a problem that many utility companies try to solve, often using black-box supervised classification algorithms. In general, this approach achieves good results. However, in practice, NTL detection faces technical, economic, and transparency challenges that cannot be easily solved and which compromise the quality and fairness of the predictions. In this work, we contextualise these problems in an NTL detection system built for an international utility company. We explain how we have mitigated them by moving from classification into a regression system and introducing explanatory techniques to improve its accuracy and understanding. As we show in this work, the regression approach can be a good option to mitigate these technical problems, and can be adjusted in order to capture the most striking NTL cases. Moreover, explainable AI (through Shapley Values) allows us to both validate the correctness of the regression approach in this context beyond benchmarking, and improve the transparency of our system drastically.

show abstract

Explainable Predictive Process Monitoring

Cited by 55 publications

References 17 publications

Explainable Predictive Process Monitoring

Explainable Predictive Process Monitoring

The Duo of Artificial Intelligence and Big Data for Industry 4.0: Review of Applications, Techniques, Challenges, and Future Research Directions

Non-technical losses detection in energy consumption focusing on energy recovery and explainability

Contact Info

Product

Resources

About