Combining deep ensemble learning and explanation for intelligent ticket management

• Published in: Expert systems with applications 2022-11, Vol.206, p.117815, Article 117815
• Main Authors: Zicari, P., Folino, G., Guarascio, M., Pontieri, L.
• Format: Article
• Language: English
• Subjects: Ensemble of deep neural networks; Interpretable machine learning; Prediction explanation; Ticket classification
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2022.117815

Intelligent Ticket Management Systems, equipped with automated ticket classification tools, are an advanced solution for handling customer-support activities. Some recent approaches to ticket classification leverage Deep Learning (DL) methods, in place of traditional ones using standard Machine Learning and feature engineering techniques. However, two challenging objectives should be addressed when applying DL methods to real-life contexts: (i) curbing the risk of having an overfitting model that hinges on spurious ticket features, and (ii) trying to explain the ticket classifications returned by such black-box models. In this work, we propose a comprehensive ticket classification framework, which relies on training a novel kind of ensemble of deep classifiers, and on providing AI-based interpretation methods to help both the operator in recognizing misclassification errors and the analyst in improving and fine-tuning the model. Tests on real data confirmed the accuracy of the classifications returned by the framework, and the practical value of their associated explanations. •A framework of deep ensemble classifiers is proposed for ticket classification.•Two novel combiners extending stacking and MOE schemes are introduced.•Intelligible visual artifacts are provided for classification explanation.•A human in the loop scheme is provided for intelligent ticket management.•Extensive tests on two real-life case studies permit to validate the approach.