• Manjot Kaur
• Er. Amandeep Kaur Sohal
• Er. Amanpreet Singh Brar

The prediction analysis can be done with three steps (a) pre-process (b) feature extraction and (c) classification. The predication analysis models are designed according to application type such as crop production analysis is one of the applications of prediction analysis. The model is trained using the sample data that includes known attributes which are High level production, Medium level production and Low level production. New data is analyzed and its behavior is determined using the trained model. In this paper, the KNN classifier is applied for the crop prediction in India. To improve accuracy of the existing algorithm the KNN classifier is replaced with the naïve bayes classifier for the wheat production prediction. The proposed and existing work is implemented in python and compared with each state of art. Simulation results show that proposed work improves the accuracy with reduction in execution time.

KNN, Naives Bayes, Wheat production

"Machine Learning Approach For The Wheat Production Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.762-767, June 2019, Available :http://www.jetir.org/papers/JETIR1906N15.pdf

"Machine Learning Approach For The Wheat Production Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp762-767, June 2019, Available at : http://www.jetir.org/papers/JETIR1906N15.pdf