This study introduces XAI-CROP, an innovative algorithm that integrates explainable artificial intelligence (XAI) principles to enhance crop recommendation systems (CRS). The primary objective of XAI-CROP is to provide farmers with transparent insights into the recommendation process, addressing the transparency and interpretability issues often associated with conventional machine learning models. The study compares XAI-CROP with several prominent machine learning models, including Gradient Boosting (GB), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), and Multimodal Naïve Bayes (MNB). Performance evaluation is conducted using three key metrics: Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R²). The empirical results show that XAI-CROP outperforms the other models, achieving a low MSE of 0.9412, an MAE of 0.9874, and an R² value of 0.94152. These metrics indicate highly accurate crop yield predictions and strong interpretability, respectively. The study also highlights the importance of XAI in enhancing the reliability and trustworthiness of machine learning models in agricultural decision-making. The research contributes to the field by providing a robust framework for developing transparent and interpretable crop recommendation systems, which can significantly benefit farmers, agricultural managers, and researchers. The findings suggest that XAI-CROP can optimize crop yields, minimize resource wastage, and enhance overall profitability in agricultural operations. Future work could explore the application of XAI-CROP in various optimization tasks, natural language processing, and supply chain management.This study introduces XAI-CROP, an innovative algorithm that integrates explainable artificial intelligence (XAI) principles to enhance crop recommendation systems (CRS). The primary objective of XAI-CROP is to provide farmers with transparent insights into the recommendation process, addressing the transparency and interpretability issues often associated with conventional machine learning models. The study compares XAI-CROP with several prominent machine learning models, including Gradient Boosting (GB), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), and Multimodal Naïve Bayes (MNB). Performance evaluation is conducted using three key metrics: Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R²). The empirical results show that XAI-CROP outperforms the other models, achieving a low MSE of 0.9412, an MAE of 0.9874, and an R² value of 0.94152. These metrics indicate highly accurate crop yield predictions and strong interpretability, respectively. The study also highlights the importance of XAI in enhancing the reliability and trustworthiness of machine learning models in agricultural decision-making. The research contributes to the field by providing a robust framework for developing transparent and interpretable crop recommendation systems, which can significantly benefit farmers, agricultural managers, and researchers. The findings suggest that XAI-CROP can optimize crop yields, minimize resource wastage, and enhance overall profitability in agricultural operations. Future work could explore the application of XAI-CROP in various optimization tasks, natural language processing, and supply chain management.