Comparative decision models for anticipating shortage of food grain production in India
2018
Chattopadhyay, Manojit | Mitra, SubrataKumar
This paper attempts to predict food shortages in advance from the analysis of rainfall during the monsoon months along with other inputs used for crop production, such as land used for cereal production, percentage of area covered under irrigation and fertiliser use. We used six binary classification data mining models viz., logistic regression, Multilayer Perceptron, kernel lab-Support Vector Machines, linear discriminant analysis, quadratic discriminant analysis and k-Nearest Neighbors Network, and found that linear discriminant analysis and kernel lab-Support Vector Machines are equally suitable for predicting per capita food shortage with 89.69 % accuracy in overall prediction and 92.06 % accuracy in predicting food shortage (true negative rate). Advance information of food shortage can help policy makers to take remedial measures in order to prevent devastating consequences arising out of food non-availability.
Show more [+] Less [-]AGROVOC Keywords
Bibliographic information
This bibliographic record has been provided by National Agricultural Library