College Career Planning Resources using User-User-Based Collaborative Filtering with K-Nearest Neighbour Algorithm

Recently, college graduates find great assistance in achieving their professional objectives using recommender systems, which provide employment recommendations to individuals based on their interests and skill set. However, the students need to spend a lot of time gathering information in order to choose the ideal job. This research proposes a Machine Learning (ML) algorithm called User-User-Based Collaborative Filtering with K-Nearest Neighbor (UUBCF-KNN) to evaluate the effectiveness of the teaching model for college career planning learning resources under different academic institutions. The Knowledge dataset is initially utilized to collect student data, then collaborative filtering locates persons with similar preferences based on predetermined goals. KNN then selects the nearest users based on their past selections and performance. Through analysis of these similar people, the system effectively provides customized career recommendations. Therefore, UUBCF-KNN is used to increase recommendation accuracy by fusing user similarities with pertinent and localized decision-making patterns. According to the results, it illustrates when compared with existing models such as Career Decision-Making Scale (CCDS), Massive Open Online Courses (MOOCs), and Proactive Career Behaviours (PCB) the proposed UUBCF-KNN achieved better results in accuracy of 99.89% and precision of 99.72% respectively.