Developing a Recommendation Engine using Hybrid Approach
Client: A cloud-based interactive smart video platform that delivers personalized interactive videos on-demand to consumers.
Business: Increase time spent on site, number of videos watched, and repeat visits.
The Engine: Devise an engine that offers relevant recommendation dynamically and in real-time.
Real-time recommendations need to be self-learning and based on massive amounts of data getting collected on a continuous basis.
The chosen solution had to ensure:
- fault tolerance along with low latency
- scalability and the effective deployment
The model was trained using the video meta data – genre, ratings, tags etc. as well as the user current viewing behaviour/history.
The solution was integrated with the client’s data stores and exposed to developers using command line interfaces and REST APIs.