Area and Feature Guided Regularised Random Forest: a novel method for predictive modelling of binary phenomena. The case of illegal landfill in Canary Island

Analysis of landslide explicative factors and susceptibility mapping in an andean context: The case of Azuay province (Ecuador)

“…A good model must contain a high percentage of TP and TN because they represent the number of hits between predicted and actual values. In contrast, the model error is presented in the FP and FN percentage, representing overestimations and underestimations, respectively [ 109 ]. In this context, all four metrics must be closer to one.…”