The SARS-COV-2 virus of the coronavirus family was identified in 2019. This is a type of virus that infects humans and some animals, in Peru it has seriously affected everyone, causing so many deaths, which has resulted in that people be tested to rule out contagion, using laboratory methods recommended by the government of the country. Therefore, the data science methodology was used with this research, where its objective is to predict what types of people are contaminated during SARS-COV-2 by the regions of Peru, identified through laboratory methods, therefore, the "data bank" was taken by PNDA, the CSV file was used for that study, apart from the fact that it comes from the INS and the CDC of the MINSA. In which, machine learning was developed with the decision tree algorithm and then began coding, in such a way that the distribution called Anaconda was used where it is encoded in Python language, together with that distribution, Jupyter Notebook was used which is a client-server application. The results generated by this research prove that it was possible to identify the types of individuals by SARS-COV-2. These results can help prevention entities against SARS-COV-2 to apply the corresponding preventive measures in a more focused way.