Agricultural Data Analysis with Weather and Soil Using Machine Learning Models

Abstract

Data mining involves extracting valuable insights, patterns, correlations, and trends from large datasets stored in databases or data repositories. It employs statistical, mathematical, and computational techniques to unveil information not easily visible to humans. The main objective is to convert raw data into actionable knowledge. Creating a decision tree involves recursively dividing the data into subsets based on different attributes, aiming to achieve homogeneity (for classification) or minimize variance (for regression) within each subset. This paper considers agriculture and its soil chemical-related dataset for applying data mining techniques to find suitable variables for future predictions. The five decision tree approaches are decision stump, M5P, random forest, random tree, and REP tree. Numerical illustrations are provided to prove the proposed results with test statistics or accuracy parameters.