Data Scientist Platform

The Data Scientist Platform empowers data scientists to explore data sets, quickly prototype recommendation algorithms, deploy them and then measure the impact. The algorithms are designed to respect the Public Service Media remit to inform, educate and entertain, and to avoid "filter bubbles" and other typical pitfalls of recommendation systems.

Jupyter Notebook

Features overview

Features Technical Notes
Data exploration
Online IDE Online hosted Jupyter Notebook environment enabling access to data
Prototyping
Interactive Interface Through Jupyter, interactive query on data collected and easy algorithm prototyping
Sandbox Environment Access to a mirrored production environment for easy and safe prototyping
Algorithm Rollout
Abstraction of Production Configuration Algorithms developed in the sandbox can be directly deployed to production
Shadow Deployment Deploy Algorithms to a small subset of the audience
Measurement
Dashboards Analytics and monitoring of the performance and the impact of algorithms
Sharing
Shared Storage Allowing sharing of algorithms between data scientist and if desired between broadcasters