As with UBCF, we use the same
Jester5k dataset for the item-based recommender system. In this section, we do not explore the data as we have already done so in the previous section. We first remove the user data of those who have rated all the items and also those records who have rated more than
80 as follows:
library(recommenderlab) data("Jester5k") model_data = Jester5k[rowCounts(Jester5k) < 80] model_data  3261 100
Now let's see how the average ratings are distributed for each user:
The following code snippet calculates the average ratings given by each user and identifies ...