Selection of the Decision Variables for the Habanero Chili Peppers (Capsicum chinense Jacq.) Using Machine Learning

Abstract

Data science is an area that allows a gathering of data from several prospects, being at once, collaborative and multidisciplinary. It is an area so promising and open to research from different problems, including the challenges of agronomy science throughout the study of the exploitation of database knowledge. In this work, we will study if it is possible to identify some determined variable that could allow to response to the questions, ¿Is it possible to know the genotype from a habanero pepper plant, knowing some plant measure? also, ¿Is it possible to identify the yield through the plant height? The goal is to identify the proficiency of each one of the involved areas on the preparation, processing, and database, as the necessary methods and tools to gather relevant information to the expertise; derivable from techniques as Neural Networks Algorithms and Statistics. The outcome earned, prove even tho the statistics operations revealed results by a descriptive category besides a predictive one; The Neural Networks Algorithms find results within the prescriptive category, displayed on work and that represent a very interesting answer resulting from applying questions that were not obviously in basic analysis.