Random forest feature selection for data coming from evaluation sheets of subjects with ASDs

Abstract

We deal with the problem of initial analysis of data coming from evaluation sheets of subjects with Autism Spectrum Disorders (ASDs). In our research, we use an original evaluation sheet including questions about competencies grouped into 17 spheres. In the paper, we are focused on a feature selection problem. The main goal is to use appropriate data to build simpler and more accurate classifiers. The feature selection method based on random forest is used.