Feature Selection for the Low Industrial Yield of Cane Sugar Production Based on Rule Learning Algorithms

Abstract

This article presents a model based on machine learning for the selection of the characteristics that most influence the low industrial yield of cane sugar production in Cuba. The set of data used in this work corresponds to a period of ten years of sugar harvests from 2010 to 2019. A process of understanding the business and of understanding and preparing the data is carried out. The accuracy of six rule learning algorithms is evaluated: CONJUNCTIVERULE, DECISIONTABLE, RIDOR, FURIA, PART and JRIP. The results obtained allow us to identify: R417, R379, R378, R419a, R410, R613, R1427 and R380, as the indicators that most influence low industrial performance.