Study on Predicting College Students’ Career Inclinations and Providing Personalized Suggestions Based on Neural Networks

Personalized training is necessary to meet individual differences in educational attainment, opinions, job choices, and confidence since college enrollment is growing increasingly varied. To put this into practice, it will be essential to gather and assess data from a range of students, use institutional data to perform resource-effective investigations, and take into account the career prospects of learners while developing accurate teaching methods. This research shows a novel emperor penguin search-assisted artificial neural network (EPS-ANN) approach for effectively predicting college students’ career inclinations. This work uses a dataset of student academic concerts for training the proposed technique. The dataset is first preprocessed to develop the features evaluation. To extract the significant features from the normalized data, linear discriminant analysis, LDA, is used. The suggested method is used to further process these important variables to get good predictive performance. The parameters of the ANN are improved by using the EPS optimization process. The suggested approach is tested on the Python platform and examined using several metrics. Additionally, a comparison of the suggested and current approaches is done. In summary, the EPS-ANN approach outperformed other techniques in forecasting the career preferences of college students.