Supervisor

Dr Muhammad Iqbal

Programme

BSc (Hons) in Computing in IT

Subject

Computer Science

Abstract

IT support teams are facing the persistent challenge in estimating how long an incident will take to resolve. The lack of reliable predictions, planning decisions around staffing, escalation and user communication are largely guesswork. This project set out to address that gap by building a machine learning solution capable of predicting incident resolution time from details available at the point a ticket is logged.

Using the UCI IT Incident Event Log dataset, which contains 141,712 records from a real service management system, the project followed the CRISP-DM framework across six phases from business understanding through to deployment. After thorough data cleaning and preparation, three supervised regression models were trained and compared: Linear Regression as a statistical baseline, a Decision Tree Regressor and a Random Forest Regressor. The Random Forest consistently outperformed the other two models, achieving an R² of approximately 0.69 on the held-out test set and a mean absolute error of around 48 hours when predictions were converted back to actual hours. Feature importance analysis confirmed that the number of system modifications and reassignment count were the strongest predictors of how long an incident would take to resolve.

The trained model was packaged into a Gradio web dashboard that allows non-technical staff to enter incident details and receive an instant prediction with a colour-coded risk level and an estimated resolution date. The findings suggest that machine learning can provide a meaningful and practically useful improvement over experience-based estimation in IT incident management.

Date of Award

2026

Full Publication Date

2026

Access Rights

open access

Document Type

Undergraduate Project

Resource Type

bachelor thesis

Download

Share

COinS