The integration of the Internet of Things (IoT) and Machine learning (ML) techniques can enhance agricultural practices by providing real-time data and insights into the implementation of these techniques and the risks associated with them. The paper answers questions on data acquisition and farming optimization by equipping farms with sensors and analysing the data through data sets. It also focuses on crop recommendation, yield prediction, and weather forecasting, demonstrating how the integration of IoT and ML provides optimized solutions for decision-making, environmental sustainability, and improved crop yield. The analysis presents a variety of ML algorithms such as the Naïve Bayes classifier, Decision Tree, Random Forest, K-Nearest Neighbours (KNN), Regression techniques, and Support Vector Machine (SVM) that have been used to assess the ensemble techniques to evaluate their effectiveness using model accuracy and F1 score in optimizing agricultural processes. Six different data sets have been used to cover all possible scenarios. The findings highlight the potential of IoT-ML integration to improve decision-making, environmental sustainability, and crop yield. Overall, this research contributes to the advancement of smart agriculture and offers actionable insights for stakeholders in the agricultural sector.