Recommenderlab package

rstudio

#1

I was trying to do cross validation with IBCF model.

After building recommenders with methods like UBCF, IBCF and POPULAR, i was getting predicted values using UBCF and POPULAR for user say(1) and item say(500) but with IBCF i am getting NA for the sameuser and item.

Is there a specific reason that we should use "known" data in predict() function as below,can't we use "unknown" data, I was getting NA
predict(eval_ib,newdata=getData(eval_sets,"known"),n=5,type="ratings")

While calculating model accuracy by user, was getting NA for one user, is there a specific reason for that.
calcPredictionAccuracy(x=eval_pred,data=getData(eval_sets,"unknown"),byUser=TRUE)

How can I do grid search for the parameters like 'nn' in UBCF and 'k' in IBCF?, tried with evaluate().

Any suggestion will be helpful.


#2

This has been resolved.

I can do grid search of the parameters 'nn' and 'k' using lapply(). Came across a book Recommendation systems in R