# How does the “age” feature work in video recommendation systems?

In the paper Deep Neural Networks for YouTube Recommendations, it mentions that the “example age” feature helps recommending fresh contents in Section 3.3.

Many hours worth of videos are uploaded each second to YouTube. Recommending this recently uploaded (“fresh”) content is extremely important for YouTube as a product.

...

The distribution of video popularity is highly non-stationary but the multinomial distribution over the corpus produced by our recommender will reflect the average watch likelihood in the training window of several weeks.

To correct for this, we feed the age of the training example as a feature during training. At serving time, this feature is set to zero (or slightly negative) to reflect that the model is making predictions at the very end of the training window.

What is exactly is the "age"? Is it end_of_window - upload_time?
Why is it set to zero at serving time? How does it help with the freshness of the recommendation system?