Data- & compute-efficient deviance mining via active learning and fast ensembles

Detecting deviant traces in business process logs is crucial for modern organizations, given the harmful impact of deviant behaviours (e.g., attacks or faults). However, training a Deviance Prediction Model (DPM) by solely using supervised learning methods is impractical in scenarios where only few...

Full description

Saved in:
Bibliographic Details
Published in:Journal of intelligent information systems 2024-08, Vol.62 (4), p.995-1019
Main Authors: Folino, Francesco, Folino, Gianluigi, Guarascio, Massimo, Pontieri, Luigi
Format: Article
Language:English
Subjects:
Accuracy
Artificial Intelligence
Computer Science
Costs
Data Structures and Information Theory
Efficiency
Fault detection
Information Storage and Retrieval
Information systems
IT in Business
Natural Language Processing (NLP)
Prediction models
Supervised learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Detecting deviant traces in business process logs is crucial for modern organizations, given the harmful impact of deviant behaviours (e.g., attacks or faults). However, training a Deviance Prediction Model (DPM) by solely using supervised learning methods is impractical in scenarios where only few examples are labelled. To address this challenge, we propose an Active-Learning-based approach that leverages multiple DPMs and a temporal ensembling method that can train and merge them in a few training epochs. Our method needs expert supervision only for a few unlabelled traces exhibiting high prediction uncertainty. Tests on real data (of either complete or ongoing process instances) confirm the effectiveness of the proposed approach.
ISSN:0925-9902
1573-7675
DOI:10.1007/s10844-024-00841-4