An Overview of Data Mining Techniques for Maize Yield Prediction


  • M. Tamilselvi
  • B. Jaison



crop yield prediction, Maize, data mining, Apriori algorithm, SVM Classifier, Ada boost algorithm.


Agriculture is the main source for the people in India which ensures major source of economy for the country. Major harvest generation depends on suitable climatic conditions. More than 60 percent of crop depends on rainfall. However various natural disasters such as flood or lack of rainfall spoil the entire crop yield production. This leads to enormous financial loss for the farmers which in turn affect the crop production. Predicting the crop yield in advance through various attributes like rainfall, temperature, type of soil, soil nutrient, and seed rate will help the farmers and government organizations to make prior arrangement regarding sales, storage, Import/Export Details etc. Through data mining we extort the knowledge from the massive size of data. Different Data Mining Techniques can be utilized for estimating the future crop production. This paper deals with Maize crop yield prediction through Apriority Algorithm for association rule Mining and SVM classifier for dimensionality reduction. Furthermore performance of the proposed technique is improved with AdaBoost algorithm. The success of any crop yield prediction system heavily relies on how exactly the features have been extracted and how properly classifiers have been employed.



[1] G Ruß, "Data Mining of Agricultural Yield Data : A Comparison of Regression Models", Conference Proceedings, Advances in Data Mining – Applications and Theoretical Aspects, P Perner (Ed.), Lecture Notes in Artificial Intelligence 6171, Berlin, Heidelberg, Springer, 2009, pages : 24-37.

[2] R. Medar, V. Rajpurohit, “A survey on data mining techniques for crop yield predictionâ€, International Journal of Advance Research in Computer Science and Management Studies, vol. 2, no. 9, pp. 59-64, 2014.

[3] Prajneshu, R. K. (2008). Artificial Neural Network Methodology for Modelling and Forecasting. Agricultural Economics Research Review, 21, 5-10.

[4] Rossana MC, L. D. (2013). A Prediction Model Framework for Crop Yield Prediction. Asia Pacific Industrial Engineering and Management Society Conference Proceedings Cebu, Phillipines, 185.

[5] White, David, Howden, S. Mark,Climate Change: Signiï¬cance for Agriculture and Forestry,Springer,May 1994.

[6] Ramesh A. Medar,Vijay S. Rajpurohit, “A survey on Data Mining Techniques for crop yield predictionâ€, International Journal of Advance Research in Computer Science and Management Studies.Volume 2 , Issue 9, Sept 2014.

[7] Jeysenthil.KMS, Manikandan.T, Murali.E “Third Generation Agricultural Support System Development Using Data Mining†International Journal of Innovative Research in Science, Engineering and Technology Vol. 3, Issue 3, March 2014.

View Full Article: