‘CBC generates almost 500 new pieces of content each day so we need a system that can make real-time predictions and be updated with new pieces of content as they emerge.’
Canada’s public broadcaster is refining a new recommendation engine based on session preferences. Other recommender algorithms predict interest by recalling a user’s prior searches (‘you liked that song so you may like this one’) or inferring interest by similarities with other searchers (‘others that liked this book also liked these’).
The story says the CBC’s per-session approach predicts a trajectory of interest based on the items selected earlier in the visit.
The Public Service Algorithm: Personalization at the CBC
MEDIUM | October 1, 2018 | by Jason Cornell