AI-Powered Career Guidance A Scalable Model for Personalized Recommendations

This project presents an intelligent machine learning framework for career guidance and employment prediction, designed to assist students, educational institutions, and career counselors in making informed career decisions. The framework utilizes a wide range of academic, professional, and personal attributes, including educational background, academic performance, skills, career interests, entrepreneurial aspirations, prior work experience, industry preferences, and user satisfaction metrics, to predict suitable career paths and employment outcomes. A comprehensive data preprocessing pipeline was implemented, incorporating missing value handling, categorical feature encoding, feature scaling, class balancing using SMOTE, and train-test splitting to ensure reliable model performance. The proposed framework introduces a novel Adaptive Cross-Fusion Ensemble Network (ACFE-Net) that integrates deep latent feature extraction through an Autoencoder with powerful ensemble learning algorithms, namely CatBoost, Extra Trees, and HistGradient Boosting classifiers. An attention-based neural meta-learner is employed to intelligently combine the predictions of the base models, enhancing classification accuracy and generalization capability. To evaluate the effectiveness of the proposed approach, two advanced deep learning architectures, Dual-Tower Feature Extraction Network (DTFE-Net) and Hybrid Residual Attention Fusion Network (HRAF-Net), were also developed for comparative analysis. Experimental results demonstrate the superior performance of ACFE-Net in capturing complex nonlinear relationships among career-related factors and generating accurate employment predictions. The trained models were saved for deployment and real-time inference applications. The proposed framework provides a scalable and reliable solution for personalized career recommendation, workforce planning, and educational decision support, ultimately contributing to improved employability and career development outcomes.

Keywords: Career Guidance Prediction, Employment Prediction, ACFE-Net, Autoencoder, CatBoost, Extra Trees, HistGradient Boosting, Attention-Based Meta Learning, DTFE-Net, HRAF-Net, Deep Learning, Ensemble Learning, Educational Analytics, Career Recommendation System, Predictive Analytics.