Predicción para el Negocio de Alquiler de Automóviles con Técnicas Supervisadas

Abstract

Car rental is a new trend and is already a reality in many countries, as it is a cheaper option than maintaining your own. The objective of this article is to identify the ideal car for a person, according to the characteristics that you want. In the present work, a study was made of the previous steps involved in the prediction of a car according to the desired characteristics and a comparison of the classification algorithms was carried out to determine which classification is appropriate in terms of the accuracy of the prediction. The steps followed were: Data collection, preprocessing, data preparation and comparison of classification algorithms. The results obtained show that the Random Forest algorithm presents a 95.12% correct classification of the instances and a mean square error of 0.12, which are acceptable results for the tests performed.