Tutorial: How to determine the quality and correctness of classification models? Introduction

Classification schemes keep evolving & improving with recent publications. Those recent techniques involve multi-output classifications, ie, the response variable/s is 2 or more in comparison to standard classification of just a single variable say Y. The multi-class MIMO SVR (multi input multi output - support vector regression) is one of those new techniques, eg: the multi output could be 3 variables (as Gender, Age-bracket, Earning-bracket) & may be denoted as [G, A, E], where gender is 2 class (male, female), age-bracket is multiclass (student, young-adult, adult, retired) & age-bracket is also multiclass. MIMO SVR can predict the 3 output variables class labels at once. The other multiclass MIMO schemes includes CANFIS (Co-Active Neuro-Fuzzy Inference System) & its variants.