This study aims to determine the characteristics of young farmers and their businesses that benefit from and cannot benefit from young farmer support in the Mediterranean Region and determine the factors that affect the benefit of young farmer project support. In 2016, a survey was conducted with all 160 producers who benefited from young farmer support, and a survey was conducted with 56 producers who applied for young farmer project support but could not benefit from it to make comparisons between groups. The tendency of farmers to benefit from the young farmer support project was determined using artificial neural networks and logistic regression analysis. It was determined that the majority of the producers who received support only made animal production and mixed production (livetock production and vegetable production), while the majority of the producers who did not receive support made only plant production. With both analysis methods, it was determined that the most critical variables that affect the benefit of young farmer project support are the type of activity, the share of non-agricultural income in total income, the number of farmers in the family, the education period, the status of having non-agricultural income and family size. The total correct classification rate was found to be 87.04% in the logistic regression analysis and 91.20% in the artificial neural network analysis, and it was seen that the classification percentages obtained by both methods were quite close to each other.

This study aims to determine the characteristics of young farmers and their businesses that benefit from and cannot benefit from young farmer support in the Mediterranean Region and determine the factors that affect the benefit of young farmer project support. In 2016, a survey was conducted with all 160 producers who benefited from young farmer support, and a survey was conducted with 56 producers who applied for young farmer project support but could not benefit from it to make comparisons between groups. The tendency of farmers to benefit from the young farmer support project was determined using artificial neural networks and logistic regression analysis. It was determined that the majority of the producers who received support only made animal production and mixed production (livetock production and vegetable production), while the majority of the producers who did not receive support made only plant production. With both analysis methods, it was determined that the most critical variables that affect the benefit of young farmer project support are the type of activity, the share of non-agricultural income in total income, the number of farmers in the family, the education period, the status of having non-agricultural income and family size. The total correct classification rate was found to be 87.04% in the logistic regression analysis and 91.20% in the artificial neural network analysis, and it was seen that the classification percentages obtained by both methods were quite close to each other.