A Review on Text Supervised Learning Methods for Classification of IT Ticket and Bugs

Background: The corporate world deals with task management in a variety of ways all having some form of triaging process to correctly assign tickets to developers. Automation of this task has proven elusive with less accuracy for Web and SaaS companies that handle high volumes of tickets in the form of exceptions, support requests, user-reported bugs, and crash reports. Purpose: This paper analyzes different Machine Learning and Deep Learning algorithms for predicting assignees for new tickets based on past tickets. The key area of work was to investigate the usefulness of various machine learning (ML) methods to accurately construct mathematical models for predicting bugs and tickets. Method: The paper highlights the important of features Term Frequency Inverse Document Frequency (TF-IDF) and relevant data word rate to ensure high accuracy is obtained by the utilized ML models. Conclusion: In this Review will discuss about Text Supervised Learning Methods for IT Ticket and Bugs classification using its pros and cons. Also gives future idea about IT Ticket and Bugs classification.