The rapid advancement of technology in the agricultural sector has provided new opportunities for optimizing crop selection and management through data-driven approaches. However, traditional farming methods often lack the precision required to maximize yield while minimizing resource use, which poses a challenge in the face of growing global food demand. This study addresses the problem by developing a machine learning model to predict the optimal crop based on environmental factors such as Nitrogen, Phosphorus, Potassium, temperature, humidity, pH, and rainfall. Using a publicly available dataset on smart agricultural production, we employed Random Forest classifiers and K-Means clustering to classify crop types and identify patterns within the data. The model was evaluated using standard performance metrics, including accuracy, precision, recall, and F1-score, achieving an overall accuracy of 99%. Additionally, feature importance analysis revealed that rainfall, humidity, and potassium were the most influential factors in crop recommendation. The K-Means clustering technique further identified distinct crop groups based on environmental variables, which supports the classification results. The findings of this research provide critical insights for precision agriculture by helping farmers select the most suitable crops based on real-time environmental conditions. This can lead to optimized resource use, improved crop yield, and more sustainable farming practices. Future work will explore the integration of dynamic datasets and real-time data feeds to enhance the applicability of the model in real-world scenarios.