Machine learning based on extended generalized linear model applied in mixture experiments

Abstract

When performing mixture experiments, we observe that maximum likelihood methods present problems related to the collinearity, small sample size, and over/under dispersion. In order to overcome these problems, this investigation proposes a model built in accordance with a machine learning approach. This approach will be called Boosted Simplex Regression, which has been evaluated both in terms of accuracy and precision for the odds ratio. The advantages of this new approach are illustrated in a mixture experiment, which has made us conclude that the model Boosted Simplex Regression has unveiled not only better fit quality but also more precise odds ratio confidence intervals.