The classification of Capsicum spp. varieties is often hindered by their morphological similarities, making accurate identification a challenging task. To address this issue, this study applies a hybrid computational approach that combines data dimensionality reduction techniques using Principal Component Analysis and Factor Analysis with various supervised Machine Learning algorithms. The dataset, which is unprecedented in the literature and was collected under controlled agricultural conditions, enables a robust evaluation of models including Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Random Forest, Decision Tree, and Gradient Boosting. Model performance was assessed using Leave-One-Out and K-Fold cross-validation methods. Additionally, the SHapley Additive exPlanations method was applied to assess the importance of the features in species classification, providing greater interpretability that reinforces the relevance of morphological and agronomic descriptors in differentiating pepper varieties. The results show that all models achieved high performance metrics, including accuracy, F1-score, precision, and recall, consistently above 0.89, validating the effectiveness of the proposed approach. These findings highlight the potential of integrated Machine Learning frameworks for species classification in agriculture, contributing to practical applications and advancing intelligent analysis of biological data.