Identifying Factors Affecting Non-curent Debts of Banks Using Neural Networks and Support Vector Machine Algorithm

The main purpose of this paper is to identify the factors influencing the creation and increase of non-current debts to make a more appropriate decision in granting facilities. For this purpose, to select effective variables, from the analysis algorithms of correlation and Lasso components; And to classify the samples, neural networks and support machine were used. In this study, a sample of 660 legal customers of Sepah Bank for the years 2006-2017 was selected and focused on the characteristic variables extracted from the facility contracts of these customers along with financial, non-financial, auditing and economic variables. The results showed that the Lasso algorithm focused on financial, economic and auditing variables, performed better than the neighboring component analysis algorithm, and based on this algorithm, 10 key variables affecting non-current debts were identified. Due to the better performance of support vector machines with radial cores, its use in modeling non-current debts is recommended.