Predicción para el Negocio de Alquiler de Automóviles con Técnicas Supervisadas

Published in: Industry, Innovation, and Infrastructure for Sustainable Cities and Communities: Proceedings of the 17th LACCEI International Multi-Conference for Engineering, Education and Technology
Date of Conference: July 24-26, 2019
Location of Conference: Montego Bay, Jamaica
Authors: Sandra Zapata-Quentasi (Universidad Nacional de San Agustín de Arequipa, PE)
Alba Yauri-Ituccayasi (Universidad Nacional de San Agustín de Arequipa, PE)
Rodrigo Huamani-Avendaño (Universidad Nacional de San Agustín de Arequipa, PE)
Jose Sulla-Torres (Universidad Nacional de San Agustín de Arequipa, PE)
(Universidad Nacional de San Agustín de Arequipa)
Full Paper: #371

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.