Categorical Encoding for Machine Learning

Abstract: In recent years, interest has grown in addressing the problem of encoding categorical variables, especially in deep learning applied to big-data. However, the current proposals are not entirely satisfactory. The aim of this work is to show the logic and advantages of a new encoding method that takes its cue from the recent word embedding proposals and which we have called Categorical Embedding. Both a supervised and an unsupervised approach will be considered.