In 2021 I began a foundation degree with Carlisle College which is in principle the first two years of a traditional degree with the option to complete a third top up year which completed the degree and the student would receive a BSc in Applied Computing. Having so little experience in IT these were some of the hardest learning years, each topic was new and if I did have some experience in the subject then the depth and bread of knowledge required was increased. However, I credit these years in giving me the confidence to go forward and pursue a career in IT. I remember walking out on my last day having graduated with a first class and thinking this is the proudest day of my life. Training to become an IT professional was harder than becoming a train driver, not only did I learn technical skills I had to learn patience, resilience, self-belief and how to be a better student and academic. Each practical module followed a consistent format where we first learnt the theory, ethics, legislation and security considerations followed by a build assignment. In summary: Year 1: Academic Skills Structured Query Language (SQL) Databasing introduction to Non-SQL Mongo DB Dynamic Website with PHP Computational Maths Core Concepts of Programming with C++ Fundamentals of Networking inc use of Packet Tracer, Subnet Masks and Cabling Year 2 Network Management Active Directory Network Management with Powershell Project Management Secure Website and Server Management (Hardening Methods) ISO27001 App Development with the Flutter Framework Object Orientated Programming Year 3 Digital Forensics inc Legislation. Penetration Testing with Ethics and Legislation Collaborative Development Common Research Methods with Visualisation of Results. Systems Development in C## For my dissertation I began an ambitious project to bring together all the skills I had learnt in the previous three years, therefore demonstrating my comprehension of both the theoretical and practical understanding of the principles of Computer Science. I stated that I wished to explore the feasibility of implementing predictive Artificial Intelligence to identify sections of the railway that would require rail head treatments during the leaf fall season. This could potentially save the rail industry both time and money by reducing the number of resources required and un-unnecessary treatments. In summary I planned and self-project managed my project where I designed and created parts of system that rail users could use to predict sections of railway to treat during the leaf fall system. I began the project with a comprehensive literary review of the subject using a chronological style. My research included both primary and secondary and included both qualitative and quantitative data from sources such as UK based train drivers and Mr Phil Kirkland of RATW consultancy who provided an invaluable contribution to the research. To plan the practical element I designed and implemented an industry standard Gantt chart for time management, both flowcharts and wire frames to visualise how the system would function and look. To manage risk, a risk assessment was carried out using a risk matrix and user stories were created to base the system requirements on. To create the app several Integrated Development Environments (IDEs) were considered and I selected Visual Studio, because of its ability to hot reload and its version control functionality. Due to a lack on Data Science skills Google Vertex was selected to provide the Machine Learning as a Service, Microsoft Azure's learning materials were superior however a successful model could not be created vs Vertex. To manage, clean and process the pre-requisite data I selected the industry standard products such as Excel and MySQL workbench for tabular data, role based permissions and size and scope of the data set. MongoDB was considered however it was dismissed due to a lack of SQL functionality. The app featured industry standard functionality such as Create, Read, Update and Delete (CRUD) and a dynamic connection between the app and the database held within MySQL. Lastly the app was reviewed and critiqued by two industry professionals one being a senior software developer for a rail industry division IT provider, he commented that the UI operated well and was close in design to some programs already in existence. The conclusions identified that it was in fact feasible to develop and implement a system that utilised predictive AI however the project was constrained by the time, the author's skill set and experience. Commercial viability was beyond the scope of the project however, the system could be described as simple compared to other systems in development and was subject to legal, regulatory practices, ethical considerations and there was a risk of duplication. Lastly, a gap in knowledge was identified, this included to what degree would primary stakeholders such as train drivers extend their approval or rejection of an AI based system.