Along with it's members, EBU has built over the last few years a comprehensive ecosystem that supports all aspects required for user-centered content recommendation.
The solution is composed of 5 steps. Even though there might be multiple components behind each of them, they can be seen as the 5 logical steps required for an integration of content recommendation:
- Collect : collect and store events produced by users during usage of mobile apps, web portals and other digital products. More in Data Collection. Use CODEX to store metadata and transcript of your media.
- Explore : The PEACH Lab provides Data Scientist with a complete in the Cloud solution to inspect raw data to determine quality, compute metrics to understand behaviours and define which algorithms would the most appropriate.
- Compute : Craft specific algorithms and create recommendation models. Automate the computation using Tasks.
- Deliver : use recommendation models to recommend the most relevant content to the user in real-time and deliver it to clients using REST Recommendation APIs.
- Monitor : track recommendation accuracy, performance and diversity in dashboards. Evaluate recommendations visually in Spectrum before you integrate them in production.