Estimation and prediction of an Index of Financial Safety of Tunisia

This paper analyses the strength of the financial system of Tunisia through the construction of an Index of Financial Safety (IFS). Over the period 2000Q1 – 2014Q3, the IFS is built using a wide range of financial and macroeconomic indicators. The empirical results show that it can capture the disturbances in Tunisian financial system with sufficient accuracy. The nonlinear autoregressive with exogenous input (NARX) model with Levenberg-Marquardt algorithm of training was selected to forecast changes in IFS, and provides significant results.