When Should I Change a Model Training Frequency?

The recommended training frequencies for each Data Period value shown in the following table provide optimal results for most implementations. When training a model using a longer Data Period, you cannot retrain the model as frequently.

Data Period Training Frequency
Daily Weekly Monthly
1 week
1 month
3 months
6 months
1 year

Icon-ThumbsUp_BK_16 = recommended = available

Consider increasing the training frequency when your search hubs serve at least 10,000 user queries per data period and for example your relevant content or your user behavior patterns are changing more frequently and you want recommendations to adapt more rapidly.

Consider reducing the training frequency when your relevant content or your user behavior patterns are stable over time.