In a section of my app I would like to recommend restaurants to users based on certain parameters. Some parameters have a higher weighting than others. In this WWDC Video a very similar app is made. Here if a user likes a dish a value of 1.0 is assigned to those specific keywords (that apple to the dish) with a value of -1.0 to all other keywords that don't apply to that dish.
For my app if the user has ordered I then apply a value of 1.0 (to the keywords that apply) but if a user has just expressed interest (but not ordered) then can I apply a value of 0.5 (and -0.5) instead, would the model adapt to this?
