Application of Support Vector Machine Algorithm in Predicting the Career Development Path of College Students

This paper focuses on analyzing the use of the Support Vector Machine (SVM) classifier in forecasting the career progression of college students. In this case, the research seeks to evaluate the performance of SVM in the prediction of students’ job outcomes regarding factors like GPA, extra curriculum activities, and internship. This dataset was taken with these attributes and after completing the exploration a feature selection by the Recursive Feature Elimination (RFE) was used. The model compiled the data with 80% of data for training, with the 20% of data that were used for testing, the model’s overall accuracy in prediction stood at 87%. Evaluation metrics such as precision, recall, and F1-score were used to validate the model’s performance across five distinct career paths: Academia, industry, entrepreneurship, government, and freelancing. In general, high accuracy in identifying academic and government careers was reported while freelancing and entrepreneurship were less successfully predicted possibly because of their unbound lifestyle. As stated, the study shows that SVM can indeed be used for career counseling in the educational sectors since students can be given an objective model to follow. Future enhancement includes the addition of personality variables and career choice to improve prediction for the less defined occupation types such as freelance work and self-employment.