Search results

Public debt forecasts represent a key policy issue. Many methodologies have been employed to predict debt sustainability, including dynamic stochastic general equilibrium models, the stock flow consistent method, the structural vector autoregressive model and, more recently, the neuro-fuzzy method. Despite their widespread application in the empirical literature, all of these approaches exhibit shortcomings that limit their utility. The present research adopts a different approach to public debt forecasts, that is, the random forest, an ensemble of machine learning.

Using quarterly observations over the period 2000–2021, the present research tests the reliability of the random forest technique for forecasting the Italian public debt.

The results show the large predictive power of this method to forecast debt-to-GDP fluctuations, with no need to model the underlying structure of the economy.

Compared to other methodologies, the random forest method has a predictive capacity that is granted by the algorithm itself. The use of repeated learning, training and validation stages provides well-defined parameters that are not conditional to strong theoretical restrictions This allows to overcome the shortcomings arising from the traditional techniques which are generally adopted in the empirical literature to forecast public debt.

This paper aims to develop a compound measure, which is fiscal vulnerability index, provides early warning signals of fiscal sustainability problems for Türkiye's economy.

The index is constructed using twelve distinct fiscal indicators and applying the portfolio method, which considers the time-varying cross-correlation structure between the subindices.

Dynamics of the fiscal vulnerability index indicate that it accurately predicts to the well-known fiscal crisis occurring in Türkiye's recent history. As a result, such a compound measure should be used in the early identification of fiscal vulnerability in Türkiye.

The main contribution of this paper, relative to existing papers, is that a fiscal vulnerability index was constructed by employing the most contemporaneous method and evaluating its performance in terms of capturing historical stress periods.