A CONTENT-BASED RECOMMENDATION SYSTEM FOR ONLINE COURSES

The Content-Based Recommendation System successfully addresses the challenges associated with discovering suitable online courses across multiple educational platforms. By integrating course data from Coursera and Udemy and applying TF-IDF vectorization, cosine similarity, and popularity scoring within a hybrid ranking framework, the system provides accurate and personalized course recommendations that are not limited to a single provider. Beyond recommendation, the system includes Wishlist management, four-stage learning-progress tracking, and automatic resume generation, making it a comprehensive learning-to-career support platform. The Flask-based architecture, SQLite database, and scikit-learn pipeline together provide a  lightweight,  scalable,  and  efficient solution suitable for learners seeking structured career development, and experimental results confirm both its relevance and its responsiveness.

[1]  N. Algarni and J. Sheldon, "Systematic Review of Recommendation Systems for Course Selection," Machine Learning and Knowledge Extraction, 2023. [2]  J. Li and Z. Ye, "Course Recommendations in Online Education Based on Collaborative Filtering Recommendation Algorithm," Complexity, Wiley, 2020. [3]  "Research on Personalized Distance Education Recommendation System Based on Deep Learning," Scientific Reports, Nature, 2025. [4]    R. Gugnani and H. Misra, "Implicit Skills Extraction Using Document Embedding and Its Use in Job Recommendation," AAAI Conference on Artificial Intelligence, 2020. [5]      "Collaborative Filtering Recommendation Algorithm Based on TF-IDF and User Characteristics," Applied Sciences, MDPI, 2021. [6]   C. Kavyashree, H. S. Vimala, and J. Shreyas, "Improving Oral Cancer Detection Using Pretrained Model," 2022 IEEE 6th Conference on Information and Communication Technology (CICT), 2022. [7]       Scikit-learn Documentation — TF-IDF Vectorizer and Cosine Similarity. https://scikit-learn.org/stable/modules/feature_extraction.htm l [8]   Flask Official Documentation — Application Structure and      Blueprints. https://flask.palletsprojects.com/en/3.0.x/bluepr ints/ [9]        Pandas Documentation — DataFrame Operations and CSV Handling. https://pandas.pydata.org/docs/ [10]  ReportLab User Guide — PDF Generation in Python. https://www.reportlab.com/docs/reportlab-userguide.pdf