The Development of the Credit Rating System in Agricultural Cooperative Loan Portfolio of the Bank for Agriculture and Agricultural Cooperatives

Abstract

The objective of this study was to develop the agricultural cooperative credit rating system for managing risk in the loan portfolio of the Bank for Agriculture and Agricultural Cooperatives (BAAC), an important agricultural financial institution in Thailand. The Logit model and the Artificial Neural Network (ANN) model were developed to identify the probability of default from the risk factors. The current ratio, equity multiplier ratio, debt to total assets ratio, return on equity ratio, logarithm of transaction, logarithm of loan size and quality level were important factors in determining of the probability of default in the agricultural cooperative debtors. The models were tested for reliability and validity of the prediction power in discriminating the debtors. The results from the Logit model were subsequently employed to formulate the prediction equation of the probability of default and credit rating system. The results were shown how agricultural cooperatives exposures can be managed on a portfolio basis which will enable the BAAC to diversify the risk in each of portfolio share, determine the interest rate on the basis of risk, determine the interest rate structure in the portfolio and analyze for the optimal returns in the agricultural cooperative lending portfolio.