Prediction of Crop Production in India Using Data Mining Techniques

Agriculture sector is the primary source of food and plays a major role for the Indian economy and employment. India is the top producer of major crops such as Rice, Wheat and Maize. Data mining is the study of extracting useful information from the data sets. The present study focuses on the application of data mining techniques to predict future production of crops such as Rice, Wheat and Maize with respect to various parameters observed during the period (1950-2013). The parameters considered for the study were rainfall, mean temperature, area under irrigation, area, production and yield. The regression algorithms used in the study were Multiple Linear Regression, Random Forest Regression and Multivariate Adaptive Regression Splines (Earth). The experimental results show that the performance of Multivariate Adaptive Regression Splines (Earth) is better than Multiple Linear Regression and Random Forest Regression for Rice and Wheat dataset and the performance of Multiple Linear Regression is better than Random Forest Regression and Multivariate Adaptive Regression Splines (Earth) for Maize dataset.