Objectives: To develop a prognostic reasoning model for discovering insights about the areca nut crop and to recommend an optimal strategy for improving crop productivity and heightening the lifetime of the areca nut tree using a statistical feature selection technique namely Kolmogorov-Smirnov (KS) test and data analytics approach. Methods: Data for the study was gathered by distributing questionnaires to farmers cultivating the areca nut crop in the Mangaluru region. Farmers can plan ahead of time to improve crop yield and estimate the lifetime of the tree with this strategy. The Kolmogorov-Smirnov test is employed for the pre-processed data, and optimal features are selected. To forecast crop yield and tree lifetime, various classifiers namely decision tree, support vector machine (SVM), and artificial neural network (ANN) are applied to 300 test samples and their performance is evaluated. Findings: The findings of the experiment show that the decision tree works better than other classifiers for crop yield and tree lifetime with a prediction accuracy of 96 % and 94.66 % respectively. Novelty: The proposed study performs the extraction of significant features of the areca nut crop using the KS test that results in the prediction of agricultural production and forecasting tree lifetime.