H.D.Gadade et al, International Journal of Computer Science and Mobile Computing, Vol.8 Issue.3, March- 2019, pg. 161-165 © 2019, IJCSMC All Rights Reserved 161 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X IMPACT FACTOR: 6.017 IJCSMC, Vol. 8, Issue. 3, March 2019, pg.161 – 165 A Survey on Predictive Analysis in Agricultural Soil Health Data to Predict the Best Fitting Crop H.D.Gadade 1 ; Riddhi Singh 2 ; Vaishali Chaudhari 3 ¹ ,2,3 Government College of Engineering, Jalgaon, India 1 gadade4u@gmail.com; 2 riddhis139@gmail.com; 3 vaishalic288@gmail.com Abstract— Agriculture hold an important sector in the Indian economy as it contributes around 18% of India’s gross domestic product (GDP). India is an agricultural based country where more than 50% of the population depends on agricultural. Hence there is a need to provide farmers with the effective technology and knowledge to yield better crops based on the type of soil. Different types of soil are present in India. Different types of soil have different mineral contents and each crop require different mineral components for their better growth. Each soil has certain specific characteristic and is suitable to grow only certain number of crops. Hence a farmer should know about the type of soil he possesses so that he can cultivate better crops. In this paper we have described various effective algorithms and neural network techniques which have been used to classify the soil data based on the mineral contents and predict the best suitable crop for it. Keywords— Data mining, Neural Network, Agriculture, Soil Data Analysis, Classification I. INTRODUCTION With the advances in the technology, size of the data being generated is huge. We can use this data to obtain the patterns that are of interest in numerous fields. The agricultural field is a field where application of the data mining would be beneficial to the farmers. Process of data mining includes discovery of patterns from large data sets. The characteristics of soil in a particular region make it more suitable for some crops. But repeated cultivation of same crops leads to decline in the soil fertility as well as buildup of chemicals which may alter the soil pH. To counter this, the alternate cultivation of the crops can be an effective measure. We can use the data mining process to the datasets available in agricultural field to predict the crop which is suitable for that particular soil. In this paper, the data mining process is applied to the dataset of the soil analysis which includes characteristics of soil like soil type and properties like percentages of nutrients in the soil. For this, we use the classification technique in which unknown samples are classified using training sets. Training sets are the sets of classified samples used to train classification technique how to perform its classification. The extraction of the data can be done by using various algorithms like naïve bayes algorithm, One-R, K-nearest neighbor algorithm