Optimización de rutas en el transporte de contenedores dentro del centro de acopio a través de un modelo de clasificación basado en Machine Learning.

Abstract

Optimization represents the most important part within a company when you want to reduce costs, increase your own positioning and improve decision making within an organization, to obtain results that provide the best quality and efficiency to the end customer. To do this, it must be recognized that currently these processes can be followed by tools that involve innovation and automation along with data analysis in a much faster and more accurate way. Thus allowing organizations to be leading players in a market that is increasingly faster, more demanding, but above all more competitive. At the business level, it is essential that organizations opt for the application of tools that involve the growth and acceleration of processes within their supply chain. The present research focuses on the development and construction of a Random Forest model for the classification of transportation routes in a more agile and less costly way, in which the aim is to obtain as a result a route that is favorable in terms of time and money for the delivery of boxes of bananas to the Port of Machala. The objective is to determine which variables to consider and that influence the routes when choosing the most convenient one. The application of Machine Learning is justified because it allows the factors involved to be classified accurately and autonomously, obtaining an objective response.