Further Enhancement of KNN Algorithm Based on Clustering Applied to IT Support Ticket Routing

Companies receive millions of tickets from their clients. Unfortunately, manual ticket routing takes time and relies heavily on human resources. To help automate the ticket routing, text classification can assist as it is the process of categorizing a document into a predetermined class based on its content. One algorithm is the K-Nearest Neighbors (KNN) which is a popular supervised technique but ranks average to lowest compared to other classification models. An improved KNN algorithm utilized clustering and improved the accuracy of the classifier. This paper proposed a further enhancement of this algorithm by adding preprocessing techniques, changing the distance formula, and computing for the k-value rather than choosing one. Two datasets of IT support tickets were used to train and test the algorithms. Results showed that this further enhanced algorithm significantly performed better than the initial algorithm with the highest accuracy score of 97.83% in one dataset while the initial algorithm performed best with an accuracy score of 86.34% using a k-value of 4 in another dataset.