Prediction of crop yield and cost by finding best accuracy using a machine learning approach

Abstract:

Among worldwide, agriculture has the significant responsibility for improving the economic contribution of the nation. However, most agricultural fields are underdeveloped due to the lack of deployment of ecosystem control technologies. Due to these problems, crop production is not improved, which affects the agriculture economy. Hence the development of agricultural productivity is enhanced based on the plant yield prediction. Agricultural sectors have to predict the crop from a given dataset using machine learning techniques to prevent this problem. The dataset analysis by supervised machine learning technique(SMLT) captures several information like variable identification, univariate analysis, bivariate and multivariate analysis, missing value treatments etc. A comparative study between machine learning algorithms has been conducted to determine which algorithm is the most accurate in predicting the best crop. The results show that we can compare the proposed machine learning algorithm's effectiveness with the best accuracy with entropy calculation, precision, Recall, F1 Score, Sensitivity, specificity, and Entropy.

Keywords: dataset, Machine learning-Classification method

Module 1: Data Validation Process and Preprocessing Technique

Module 2: Exploration data analysis of train a model by given attributes

Module 3 : Performance measurements of LR and DT

Module 4 : Performance measurements of RF and SVM

Module 5 : Performance measurements of NB and KNN

Module 6 : GUI (Graphical User Interface) package

Module 7 : Crop yield and cost Prediction