Career selection is one of the most pivotal decisions in a student's academic journey, yet a significant proportion of engineering graduates remain uncertain about the most suitable career path for their profile. Traditional career guidance approaches rely predominantly on academic performance metrics such as cumulative grade point average (CGPA), thereby neglecting critical factors including technical skills, certifications, extracurricular achievements, and professional networking activities. This paper presents an AI-Based Career Path Recommendation System designed to address these shortcomings by leveraging machine learning algorithms to provide personalized, data-driven career guidance to engineering students. The proposed system collects multidimensional student profile data encompassing CGPA, technical skill sets, certification records, and LinkedIn profile attributes. Following rigorous data preprocessing and feature selection, the system applies supervised classification models, specifically Decision Tree and Random Forest classifiers, to identify latent patterns between student attributes and industry job roles. Experimental evaluation conducted on diverse student datasets demonstrates a prediction accuracy in the range of 90–95%, substantiating the effectiveness of the proposed approach. The system significantly outperforms conventional methods by incorporating a broader attribute space and producing contextually relevant career recommendations. The findings suggest that AI-driven recommendation frameworks have considerable potential for integration into academic career counselling platforms to support informed decision-making among engineering students.

Keywords — Machine Learning, Loan Prediction, Classification, Banking System, Data Analysis