A large-scale workforce development program aimed at job seekers and workers in need of skill upgrades faced a key challenge. With thousands of courses available on its website for millions of participants, many users were unsure of which course to take next after completing one, while others didn't know where to start when selecting a course.

To solve this, an AI-based course recommendation system was developed, incorporating both content-based filtering and collaborative filtering techniques to guide participants in finding courses tailored to their needs and preferences.

• Content-Based Filtering: This method analyzes the attributes of courses (e.g., topics, skills taught, difficulty levels) and matches them to the user's interests and past course interactions, providing recommendations that align closely with their individual preferences.
• Collaborative Filtering: This approach leverages data from the behaviors and choices of similar users. By identifying patterns and similarities among users, it recommends courses that peers with similar profiles have found valuable.

As a result, participants received personalized course recommendations that aligned with their specific needs and preferences, making their learning journey more focused and effective. The implementation of these filtering techniques led to increased user engagement, higher course completion rates, and improved overall satisfaction.

Keywords: AI-Based Course Recommendation System, Content-Based Filtering, Collaborative Filtering, Personalized Learning Experience, User Engagement Enhancement, Workforce Development Program, Improved User Satisfaction.