Career Enforcement among Student Using Machine Learning Language

Abstract

The transformation of our world demands students and professionals to make essential choices about their future careers. The Career Enforcement Prediction using Machine Learning project evaluates machine learning methods for forecasting career alignment through motivational and demographic and academic factors. The analysis of the custom survey-based data set used exploratory data analysis methods to discover patterns between the variables of age, gender, preference choices and personal drive. Multiple classification models including Random Forest, Support Vector Machine, XGBoost, Gradient Boosting and K-Nearest Neighbors were integrated after the data preprocessing step and the categorical variable conversion process was completed. The evaluation of these models relied on measuring accuracy together with confusion matrix analysis and classification report evaluation to assess performance levels. The proposed model which demonstrated the best performance was saved using pickle for deployment purposes. Tools were implemented to develop an interactive web-based application through Streamlit enabling users to get real-time career alignment predictions by entering their data through an API interface. The project applies machine learning methods to practical career counseling solutions which aid individuals with their career selection choices