Inspiration
I was inspired by the idea of creating a personalized learning experience for students based on their interests, academic background, and career goals. The concept of a course recommendation system seemed like a practical application of machine learning techniques that could greatly benefit students in navigating the vast array of available courses.
What it does
It reduces the time taken to answer for the queries asked by the user for processing the user request within the less time he/she no need to wait for the executive to answer the queries.
How we built it
Data Collection: Acquired course catalogs, student enrollment histories, and feedback surveys to create a robust dataset. Data Preprocessing: Cleaned and transformed the data to ensure consistency and compatibility across different sources. Algorithm Selection: Experimented with collaborative filtering and content-based filtering to identify the most suitable approach for course recommendations. Model Training: Trained the chosen algorithm on historical user interactions to generate personalized course recommendations. Interface Design: Developed a user interface that allowed students to input their preferences and view recommended courses in a user-friendly manner. Testing and Deployment: Conducted rigorous testing to validate the system's performance and deployed it for real-world usage.
Challenges we ran into
Data Quality: Ensuring the accuracy and completeness of the dataset posed a significant challenge during the initial stages of the project. Algorithm Selection: Choosing the most effective algorithm for course recommendations required thorough experimentation and evaluation. User Feedback: Incorporating user feedback to improve the system's recommendation accuracy and relevance was a continuous challenge. Scalability: Ensuring the scalability of the system to handle a growing number of users and courses was a technical challenge that required careful planning.
What we learned.
Transformers, Streamlit, Google Palm, Langchain, Gemini API
