Bakhshi, M., Pourtahery, M., Roknadin Eftekhari, A. (2016). Developing a Model to Predict Success of Agricultural Production Enterprises Based on Their Capitals. , 18(6), 1443-1454.
M. Bakhshi; M. Pourtahery; A. Roknadin Eftekhari. "Developing a Model to Predict Success of Agricultural Production Enterprises Based on Their Capitals". , 18, 6, 2016, 1443-1454.
Bakhshi, M., Pourtahery, M., Roknadin Eftekhari, A. (2016). 'Developing a Model to Predict Success of Agricultural Production Enterprises Based on Their Capitals', , 18(6), pp. 1443-1454.
Bakhshi, M., Pourtahery, M., Roknadin Eftekhari, A. Developing a Model to Predict Success of Agricultural Production Enterprises Based on Their Capitals. , 2016; 18(6): 1443-1454.

Developing a Model to Predict Success of Agricultural Production Enterprises Based on Their Capitals

Journal of Agricultural Science and Technology
Article 1, Volume 18, Issue 6, 2016, Pages 1443-1454    PDF (232.31 K)
Authors
M. Bakhshi* 1; M. Pourtahery2; A. Roknadin Eftekhari2
1Agricultural Planning, Economic and Rural Development Research Institute, Ministry of Jihad-e- Agricultural, Tehran, Islamic Republic of Iran.
2Geography and Rural Planning Department, Faculty of Humanities, Tarbiat Modares University, Tehran, Islamic Republic of Iran.
Abstract
This study aimed to develop a recognition model in order to classify success of agricultural enterprises. To this end, the study investigated the relationship between capitals owned by the enterprise and the success level by using "Neural Network" model. This study was conducted during 2013-2014 in Zanjan County, Islamic Republic of Iran. Data was obtained through a structured questionnaire and holding interviews with 92 enterprise owners, out of 125, involved in producing agrifood. According to the results of data analysis, Multilayer Perceptron Neural Network with Backpropagation algorithm was the appropriate algorithm to cope with the whole scope of the study. Empirical analysis by SPSS indicated that the Multilayer Perceptron consisting of one hidden layer with 6 nodes was an appropriate architecture. Classification Accuracy Rate (CAR) and "Receiver Operating Characteristic (ROC)" curve were used to assess the model. Based on CAR of holdout data, the model was able to classify 86.4% of the samples correctly. Also, the study intended to reveal the relative importance of explanatory factors on enterprise success. Results indicated that human and social capitals were the more influential factors, followed by economic and environmental capitals. Therefore, to promote agricultural enterprises, policy makers and managers need to improve software and hardware assets, simultaneously.
Keywords
Classification; Neural Network; Perceptron; Pattern
References
Statistics
Article View: 123
PDF Download: 87
Statistics
Number of Journals45
Number of Issues2,171
Number of Articles24,672
Article View24,384,155
PDF Download17,531,363