Combining deep ensemble learning and explanation for intelligent ticket management
作者：
Highlights：
• 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.
摘要
•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.
论文关键词：Ensemble of deep neural networks,Ticket classification,Interpretable machine learning,Prediction explanation
论文评审过程：Received 3 January 2022, Revised 29 April 2022, Accepted 7 June 2022, Available online 14 June 2022, Version of Record 22 June 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117815
