Machine Learning-Driven Classification of Thai Mango Groups using Clustering and Random Forest

Classifying Thai mango varieties based on physical traits such as leaf shape and fruit size is challenging. This issue was addressed using K-means clustering of mango varieties followed by the Elbow, Silhouette, and Calinski-Harabasz methods to determine the optimal number of clusters. The clusters were validated and classified using a Random Forest model which achieved an accuracy of 91.26%. Results demonstrated significant improvements in the precision and efficiency of mango classification, benefiting both producers and consumers.