Smart Crop Recommender System-A Machine Learning Approach

Abstract

Machine learning has proven its efficacy in solving agricultural problems in the recent years such as crop recommendation, crop yield prediction, and many such. With the advancement in the sub-domain of machine learning i.e., deep learning, multiple problems are minutely solved in agricultural sector. This paper focuses on recommending 22 types of crops with the aid of correlation analysis, distribution analysis, ensembling, and majority voting. A three-tiered framework is proposed in order to implement the crop recommendation problem. It includes data preprocessing, classification, and performance evaluation modules. The feature analysis is done through correlation plots and density distribution followed by classification using ensembling techniques. Finally, performance evaluation is performed using majority voting technique. This article further uses ensembling with base learners i.e., decision trees, random forest, Naïve Bayes, and support vector machines using majority voting. Further, majority voting is used to decide the final performance metrics. The practical visualization of the correlation plot, density-histogram distribution plots, confusion matrices, and performance plot are presented. The accuracy achieved post implementation is 99.54& by using Naïve Bayes classifier. The majority voting ensembler has not shown much accuracy i.e., 98.52&. Thus, Naïve Bayes classifier is proved to be the best fit for this problem statement. Some challenges and future research directions are also epitomized in this article.