CROP YIELD PREDICTION AND REMEDIES RECOMMENDATION USING VARIOUS FEATURE SELECTION TECHNIQUES IN MACHINE LEARNING

Computer Science

Agriculture is the foundation of many countries' economies, particularly in India. The young generation who are new to farming may confront the challenge of not understanding what to sow and what to reap benefit from. This is a problem that has to be addressed, and it is one that we are addressing. Predicting the proper crop and production will aid in making better decisions, reducing losses and managing the risk of price fluctuations. The existing system is not deployed, unlike ours, which is done by applying classification and regression algorithms to calculate crop type recommendations and yield predictions. Agricultural industries must use machine learning algorithms to anticipate the crop from a given dataset. The supervised machine learning technique is used to analyse a dataset in order to capture information from multiple sources, such as variable identification, uni-variate analysis, bi-variate and multi-variate analysis, missing value treatments, and so on. A comparison of machine learning algorithms was conducted in order to identify which algorithm was more accurate in predicting the best harvest. The results show that the proposed machine learning algorithm technique has the best accuracy when comparing entropy calculation, precision, Recall, F1 Score, Sensitivity, Specificity, and Entropy.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.