Year: 2026
Type: article
Abstract: Support tickets are vital for providing high-quality customer service. Ensuring very customer has a positive experience, regardless of their issue, is essential. This paper explores optimizing support ticket systems identifying common algorithms and predicting ticket resolution time. Leveraging Machine Learning, specifically k-Nearest Neighbours (KNN) and Support Vector Machines (SVM), the study aims to predict resolution times using historical data. These algorithms will be evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) metrics. The goal is to assess the effectiveness of KNN and SVM in improving support processes. Accurate time predictions can help businesses allocate resources proactively, minimize delays, and streamline ticket assignments. By applying these models, organizations can enhance response efficiency and reduce the impact of unresolved issues.
Source: TEM Journal
DOI: 10.18421/tem153-07
Institution: Multimedia University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $647
OpenAlex ID: W7204278631