Machine Learning in Java - Second Edition

Adding custom rules to recommendations

It often happens that some business rules require us to boost the score of the selected items. In the book dataset, for example, if a book is recent, we want to give it a higher score. That's possible by using the IDRescorer interface, as follows:

• rescore(long, double) takes the itemId and original score as an argument and returns a modified score
• isFiltered(long) returns true to exclude a specific item from the recommendations, or false, otherwise

Our example can be implemented as follows:

class MyRescorer implements IDRescorer { public double rescore(long itemId, double originalScore) { double newScore = originalScore; if(bookIsNew(itemId)){ originalScore *= 1.3; } return newScore; } public boolean ...