A comparative study was carried out between the Simple Linear Regression and Decision Tree techniques to assess the impacts caused by harmonic generation in the distribution network at a medium-voltage substation. The aim of this dissertation is to carry out a comparative study of the results of applying the Decision Tree and Simple Linear Regression techniques to the analysis of harmonic impacts on an electrical system. The measurement campaign was carried out over a minimum period of 7 calendar days in accordance with PRODIST. The impact of these harmonics on the electrical system is very damaging for both consumers and utilities. The techniques used in this dissertation's methodology are the Decision Tree technique, which has the characteristic of building non-parametric models, and the Simple Linear Regression technique, which has the characteristic of building parametric models and simple mathematical calculations, which are easy to interpret and analyze. In this way, this dissertation has presented and applied in practice with case studies actions for analyzing harmonic impacts in electricity distribution systems.