Lending Decision Model for Agricultural Sector in Thailand

The purpose of this paper is to develop a lending decision model (credit scoring) for the agricultural sector in Thailand. The data used in this study is from Bank of Agriculture and Agricultural Cooperative (BAAC), a major lender in Thailand agricultural sector. During the period of 2001 to 2003 a total of 16,560 agricultural loans were made available. The logistic regression and artificial neural networks (ANN) were used to identify critical factors in lending decision process in the agricultural sector and to predict the borrower’s creditworthiness (probability of a good loan).

The results of the logistic regression verify the importance of total farm asset value, capital turnover ratio (efficiency), and the length of bank borrower relationship (duration) as important factors in determining the creditworthiness of the borrowers. The results show that a higher value of farm assets implies a higher creditworthiness, which lead to a higher probability of a good loan. However, the negative signs found on both capital turnover ratio and the length of bank-borrower relationship (duration), which contradict with the hypothesized signs, suggest that the borrower with a longer relationship with the bank and a higher gross income to total assets has a higher probability to default on debt repayment.

  • Resource type
  • Author Limsombunchai, V. C. Gan and M. Lee
  • Year of Publication2003
  • Region
  • LanguageEnglish
  • Number of pages7 pp.

Related Resources