Enhancement of 5G N/W System for the use of ML Algorithm Based Ticket-Reopening System for the use of Attack Prediction

This study presents a new data-driven approach that uses machine learning methods to predict when a technical ticket may reopen on customer support platforms run by telecom businesses that specialise in 5G fibre optic networks. Ensuring that service providers and end users comply to contractual obligations about perceived Grade of Service is the main goal. This study is a component of a larger joint research project on Future Networks that ELIS Technology Hub and a well-known Italian network services provider will be doing from 2018 to 2021. Various categorization techniques, such as support vector machines, decision trees, and artificial neural networks, are examined for their predictive abilities. The analysis shows that when predicting whether a watched ticket would likely be reopened, the Bayesian network classifier is the most accurate. The authors also recommend a prudent dimensionality reduction approach that effectively increases computing efficiency by doubling the size of the relevant training dataset relative to the original dataset. Numerical simulations demonstrate the effectiveness of the suggested method, proving it to be a useful tool for service providers. It is useful for determining which consumers are more likely to reopen a ticket because of unsolved technical concerns. This study makes a practical contribution to resource optimisation in operations related to customer service as well as methodological advancements by identifying the best prediction model.