Analysis of Alumni Information Using Machine Learning-Based Online Centralized Alumni Network Model

Paper-based and word-based files are the primary ways alumni data are handled. These vast amounts of data become challenging due to the many graduates each year. It is difficult to hunt for data about previous graduates to learn about their present condition. Even though many institution-wide processes exist to ensure that alumni information handbooks are always up-to-date, maintaining private relationships with alumni is costly and time-consuming for current students. This paper presents a Machine Learning-Based Online Centralized Alumni Network (ML-OCAN) model to enhance the institutional community and the community of incoming students. The proposed method uses support vector machine (SVM) algorithm to let graduates post their information while facilitating student–alumni connections and viewing filtered events provided by both the alumni and the admin. The alumni individuals and their posting messages were classified using an SVM method. There is a way for current and former students to stay in touch with one another, as well as for current and future students and other school community members. The experimental results show that everyone from the university’s administration to its alumni and the general public may benefit.