Recommender System with RFM ratings to put into Interaction matrix

Nobody has claimed this yet.

I am trying to use LightFM for recommending the places to transact at.
I have used Recency, Frequency and Monetary (RFM) to calculate the interactions between a user and a shop.
I am putting these RFM interaction into Interaction matrix.
How do i go about in such a case?
I am using BPR loss function and have tried parameter tuning.
It gives good recall and AUC score here... But the issue is that the stores whose Interaction ratings are generally high... Are being recommended less. The actual life recall doesn't match.
Please help how to proceed if I am making any mistake in creating the interaction matrix.

Start by reviewing how the RFM values are converted into LightFM's interaction matrix and how the BPR loss interprets those interactions; the issue names no file, test, or entry point. Compare the matrix semantics with the intended real-world recall, and establish a reproducible correction or documented explanation before considering the issue done.

Written by the indexing model from the issue text.