I am a stats newbie. A geoscientist with only undergrad stats training. Doing “pure” prediction, no clustering. Have generated a predictive algorithm using several different techniques. Best regression coefficient was 0.85 with K-NN. I expected to have to input geospatial data along with the data for the predictors (6) and predicted.
Can K-NN work like this or is it’s algorithm and predictions 100% spurious ?