CROP RECOMMENDER SYSTEM USING MACHINE LEARNING APPROACH

Abstract

Agriculture and its allied sectors are
undoubtedly the largest providers of
livelihoods in rural India. The
agriculture sector is also a significant
contributor factor to the country’s Gross
Domestic Product (GDP). Blessing to
the country is the overwhelming size of
the agricultural sector. However,
regrettable is the yield per hectare of
crops in comparison to international
standards. This is one of the possible
causes for a higher suicide rate among
marginal farmers in India. This paper
proposes a viable and user-friendly yield
prediction system for the farmers. The
proposed system provides connectivity
to farmers via a mobile application. GPS
helps to identify the user location. The
user provides the area & soil type as
input. Machine learning algorithms
allow choosing the most profitable crop
list or predicting the crop yield for a
user-selected crop. To predict the crop
yield, selected Machine Learning
algorithms such as Support Vector
Machine (SVM), Artificial Neural
Network (ANN), Random Forest (RF),
Multivariate Linear Regression (MLR),
and K-Nearest Neighbour (KNN) are
used. Among them, the Random Forest
showed the best results with 95%
accuracy. Additionally, the system also
suggests the best time to use the
fertilizers to boost up the yield.