Quality education is one of the key factors to develop a better society, so considering the classification of schools in a fair and reasonable measure, Australian government has defined the ICSEA scale. ICSEA stands for the Index of community Socio – Educational Advantage, and provides an indication of the socio educational background of the students from kinder-garden until year 12. Using a public dataset from the NSW government website, defining this as a classification problem different techniques. All this techniques are joined , allowed the authors to complete the feature selection in order to applied the 3 models picked for this approach support vector machines (SVM), Neural Networks (NB) ans KNN clustering. This problem was a classification tasks were implemented, the SVM models presented higher accuracy but KNN gives us a comparable accuracy and a fastest run in terms of time of running, Neural networks are able to generalize the data better and are consistently resistant to noise. SVM and KNN algorithms showed that both classifiers mapped the classes High, medium and Low with similar accuracy, SVM outperformed in terms of precision rate with average accuracy of 85% after tuning the optimal parameters.