A Survey on Crop Recommendation Using Machine Learning
M.V.R. Vivek1, D.V.V.S.S. Sri Harsha2, P. Sardar Maran3

1M.V.R. Vivek, UG Student, Department of CSE, Sathyabama University, Chennai (Tamil Nadu), India.
2D.V.V.S.S. Sri Harsha, UG Student, Department of CSE, Sathyabama University, Chennai (Tamil Nadu), India.
3P. Sardar Maran, Professor, Department of CSE, Sathyabama University, Chennai (Tamil Nadu), India.
Manuscript received on 08 February 2019 | Revised Manuscript received on 30 March 2019 | Manuscript Published on 28 April 2019 | PP: 120-125 | Volume-7 Issue-5C February 2019 | Retrieval Number: E10300275C19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Agriculture arranging assumes an imperative job in any nation. Agriculture segment gives different yields, for example, sustenance, crude material for industry, affordable lift and business. The Agriculture part contains huge information regarding factors influencing its info and yield. With advances in innovation different information mining systems are presented. These information mining methods can be utilized to dissect the multidimensional, time explicit information of horticulture area to create powerful learning from it which can be utilized to support the economy. Today, the term information mining [1][2] is an interdisciplinary procedure of breaking down, handling and assessing this present reality datasets and forecast based on the discoveries. Our case-based investigation gives observational proof that we can utilize diverse information mining arrangement calculations to group the dataset of horticultural districts based on soil properties. Moreover, we have explored the most performing calculation having amazing expectation exactness to suggest the best harvest for better yield. The proposed framework will coordinate the information got from archive, climate office and by applying machine learning calculation: Multiple Linear Regression, an expectation of most reasonable yields as indicated by current natural conditions is made. This furnishes an agriculturist with assortment of alternatives of harvests that can be developed. This exploration goes for examination of soil dataset utilizing information mining procedures. It centers around characterization of soil utilizing different calculations accessible. Another essential design is to foresee untested traits utilizing relapse procedure, and usage of computerized soil test grouping.
Keywords: Data Mining, Classification, Regression, Soil Testing, Agriculture, Machine Learning.
Scope of the Article: Machine Learning