Multimodal Machine Learning approaches for Career Prediction

Abstract

One of the most important research fields in the recent digital era is student career prediction. Choosing a career is critical for college students in the planning phase of life. However, accurately forecasting their career choice is challenging because of the diversity of each person's aspirations and ideas. Traditionally, various survey methodologies have been used to forecast a student's future career. However, those methods take significant time to predict the result. In today's digitized world, various computational approaches are utilized to forecast outcomes in various domains. Using computing ideas such as Machine Learning (ML), students' professional choices can also be predicted. Compared to traditional procedures, it takes less time and yields better results. In this research paper, the prediction of the student's career is made using ADABOOST, Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT) approaches. The dataset is trained and tested with the four algorithms, and it was observed that SVM had given maximum accuracy with 98 percent, and next to the ADABOOST with 88 percent accuracy.