Artificial Intelligence-Powered Personalised Career Guidance System

Abstract

Career guidance is the practice of providing individuals with information, advice, and support to help them make informed decisions with  respect to their education, training, skills development and subsequent career paths. Thus, supporting individuals to navigate the process  of making education and skills development choices and by extension career paths. Personalised career guidance further refines this process by tailoring recommendations to individual profiles and aspirations. With growing availability of digital data, this presents a  vast amount of data that traditional methods of personalised career guidance are incapable of handling. However, AI tools have shown  promising capability to sieve through huge volume of data to generate highly accurate and relevant recommendations for each individual, thus, this paper presents a personalised AI-based career guidance tool to overcome the limitations of the traditional  approaches. In the methodology, the structured waterfall was adopted; ensuring systematic design, implementation, and testing phases.  System modelling was accomplished through use-case, activity, class, and entity-relationship diagrams, providing a comprehensive framework for the system’s implementation and functionality. The implementation utilised Supabase for a real-time database,  authentication, and backend services, facilitating seamless integration with the AI layer. Rigorous testing, including functional, unit, and  API tests validated the platform's performance, achieving efficient execution times and accurate recommendations. User acceptance testing engaged target users, whose feedbacks were used to further refine the system, improving its practicality and user-centric design.  The recommendations engine demonstrated its adaptability by generating tailored career suggestions for diverse user profiles. This  article demonstrates the potentials of AI in personalised career guidance while highlighting the importance of structured development  and iterative user feedback.