Machine learning classification constitutes a subset of both artificial intelligence and data science. It involves training models to categorize or classify data points into predefined classes based on their distinct attributes or features. The core objective of classification is to empower the model to discern patterns and correlations within the data, enabling it to correctly assign new and unseen data points to their appropriate classes. This research, taking into consideration agriculture dataset with soil nutrient-related parameters like nitrogen (N), phosphorus (P), and potassium (K) in soil, and weather-related pieces of information like temperature, humidity, pH, rainfall, and their class label agriculture products. In this paper, we utilize the machine learning approaches to find the future prediction with accuracy parameters using logistic regression, multilayer perceptron, simple logistic, SMO, decision stump, hoeffding tree, J48, LMT, random forest, random tree, and REPtree. Numerical illustrations are also provided to prove the results and discussion.