Recommender System - Predict ratings with Random Forest Regressor or Classifier?

My dataset has clothes that contain features for every cloth. Let me show you the dataframe to understand.

Every cloth is rated between [0,10] with step 0.5

In bibliography and paper conferences some tend to use regression models for recommendation and others classifiers. Of course i understand the fact that classifiers are for categorical data and regression for continuous but in my case should we treat ratings as categorical values even if they are ordinal?

For a random forest model what will be the best option from a scientific point of view.

Any invokes to scientific articles will be appreciated