A Hybrid Continual Learning Approach for Efficient Hierarchical Classification of IT Support Tickets in the Presence of Class Overlap

A support ticket describes an issue faced by a system's end-users when they encounter issues with their system. For large-scale IT corpora with hundreds of classes organized in a hierarchy, the task of classifying support tickets is vital to guarantee long-term clients. Due to the complexity of the unstructured nature of human language, text classification is challenging. The task is even harder when classes overlap. In the business world, an efficient and interpretable ML model is preferred over an expensive black-box model. In this paper, we propose a Hybrid Online Offline Model (HOOM) for efficient classification of hierarchical text documents using linear ML models. The experimental results on a private dataset of IT support tickets show that the hybrid model (HOOM) exhibits a promising performance if deployed in a real-world scenario. Furthermore, the hybrid model is anticipated to have a fast inference time given the underlying linear classifiers.