Problem

BookWise, a book recommendation system, faced the challenge of providing personalized recommendations to its user base of 50k. The existing system lacked the ability to filter books based on user preferences and reading history, resulting in low user engagement and high churn rate.

The team realized that they needed to develop a new recommendation system that could leverage Content and Collaborative filtering algorithms to provide more accurate and personalized book recommendations.

Solution

To solve the problem, the team engineered a personalized recommendation system using Python and Jupyter Notebook. They implemented various filtering methods based on user preferences and reading history using Content and Collaborative filtering algorithms.

The new recommendation system increased user engagement by 28% and reduced churn rate by 15%. The team also added features such as book reviews, ratings, and social sharing options to enhance the user experience.

Impact

Increased user engagement by X%
Reduced churn rate by X%

Quote of how incredible of an impact this had.

Team

Team Member #1 - Data Scientist
- Leveraged Content and Collaborative filtering algorithms for personalized recommendations
- Analyzed data to identify trends in user behavior
Team Member #2 - Software Engineer
- Built the recommendation engine using Python and Jupyter Notebook
- Added features such as book reviews, ratings, and social sharing options to enhance the user experience

BookWise Improves Engagement with Personalized Recommendations