Machine Learning Framework for Career Prediction and Entrepreneurial Development

Effectual career and entrepreneurial guidance are necessary for students to negotiate for today’s dynamic job market. This study uses machine learning to predict career aspirations and entrepreneurial potential based on a comprehensive dataset of student profiles, including academic scores, extracurricular participation, and absenteeism, and self-study hours, and part time job. The objective is to grasp machine-learning algorithms (Random Forest, Decision Tree, and KNN, Naïve Bayes) to provide personalized guidance. Preprocessing steps included handling missing values and splitting data into training and testing sets. Model performance was evaluated using accuracy. Results showed that the Naïve Bayes Classifier model attaining the highest accuracy (96%), with part time job being the most influential factors. These findings illustrate the potential of predictive modeling in improving career planning. This research points out the value of integrating machine learning into career guidance systems and sets the stage for further exploration with larger datasets and advanced techniques.