Datathon'22 - Winners
Description
Participating in the All Island Data Science and Machine Learning Competition was an exhilarating journey. This competition was a comprehensive evaluation of our data processing and analysis capabilities, pushing us to craft creative solutions from the insights derived. The final task was a real test of our skills, where we had to develop a recommendation model to suggest insurance premiums for potential customers. Our approach evolved from a user-based recommendation system to a sophisticated collaborative filtering model, ultimately implementing advanced non-negative matrix factorization and ALE distribution models for higher recommendation performance.
Technologies
Key Achievements
- Recommendation Model: Our transition from a basic user-based system to advanced models showcased our adaptability and problem-solving skills.
- Advanced Techniques: Implementing non-negative matrix factorization and ALE distribution models highlighted our proficiency in cutting-edge methodologies.