A Comparison of Classification Algorithms for Predicting Dis-tinctive Characteristics in Fine Aroma Cocoa Flowers Using WE-KA Modeler

The expression of crop functional traits is influenced by environmental and management conditions, which in turn is reflected in genetic diversity. This study employed a data mining approach to determine the functional traits of flowers that influence cocoa diversity. A total of 1,140 flowers from 228 trees were utilized in this study, with 177 representing fine aroma cocoa trees and 51 trees belonging to other commercial cultivars. Three attribute evaluators (InfoGainAttributeEval, CorrelationAttributeEval and GainRatioAttributeEval), and six algorithms (Naive Bayes, Multinomial Logistic Regression, J48, Random Forest, LTM and Simple Logistic) were employed in this study. The findings indicated that the GainRatioAttributeEval attribute generator was the most efficacious in discerning the functional trait in cocoa diversity flowers. The algorithms Simple Logistic and LMT were the most accurate and specific, while Naive Bayes was the most efficient in terms of computational complexity for model building. This research provides a comprehensive overview of the use of machine learning to analyze functional traits of flowers that most influence cocoa genetic diversity. It also highlights the need to further improve these models by integrating additional techniques to increase their efficiency and extend the data mining approach to other agricultural sectors.