I use the Tensorflow Recommender (TFRS) and get recommendations for previously watched movies https://www.tensorflow.org/recommenders/examples/basic_retrieval
The manual says:
...The model is re-recommending some of users' already watched movies. These known-positive watches can crowd out test movies out of top K recommendations... ..can be tackled by excluding previously seen movies from test recommendations.
How can I exclude previously watched movies from test recommendations? At what stage should this be done?