The aim of this study is to determine the relationship between banking off-balance sheet transactions and macroeconomic variables. For this purpose, off-balance sheet transactions were used as dependent variables in the study, and total assets, equity size and profitability were determined as on-balance sheet independent variables. The non-parametric Multivariate Adaptive Regression Splines (MARS) method, which assumes the functional relationship between dependent and independent variables, was used as the analysis method in the study. As a result of the study, it is seen that all P probability values of the variables are lower than 0.01 and are significant. It is understood that the whole of the model is significant because the F-statistic value is 88.97833 and its significance is 0.0000. R squared is 87%, indicating that the independent variables have high explanatory power for the dependent variable. There are seven basic functions in the model, and it was observed that the size of equity, total assets, profitability, exchange rate and total required reserves have an effect on off-balance sheet transactions. According to the model, it is seen that the active variable affects the off-balance sheet transactions in all values it receives. Again, when the model is examined closely, it is seen that the equity variable is effective in determining the size of off-balance sheet transactions at values greater than 1,378, the exchange rate variable with values greater than 1256.33, and the total reserve requirement variables greater than 4,69932.