The paper provides, for the first time, the analysis of the quality of the GDP growth and inflation forecasts by multiple forecasters for the Croatian economy. Forecast data of 6 different institutions in the 2006-2015 period are analysed. Efficiency and biasedness test are conducted following the Davies and Lahiri econometric framework based on a three-dimensional panel dataset which includes multiple individual forecasters, target years and forecast horizons. In order to assess directional accuracy we follow the approach by Pesaran and Timmermann. Based on MAE values we find the forecasts to be accurate on a scale comparable to the European Commission's forecast reported in 2016 for the EU and the euro area. GDP growth forecasts exhibit a strong bias related to a notable tendency to over-predict GDP growth. In the case of inflation forecasting the bias is still present for all forecasters, albeit less pronounced and not statistically significant for all of them. There is evidence of forecast inefficiency regarding both analysed variables. Overall, inflation forecasting presents less of a challenge due to specific monetary policy strategy and inaccurate national accounts data accompanied by extended revision process of the GDP data by the government's statistics office.
Abstract.Over the past few decades, data mining techniques, especially artificial neural networks, have been used for modelling many real-world problems. This paper aims to test the performance of three methods: (1) an artificial neural network (ANN), (2) a hybrid artificial neural network and genetic algorithm approach (ANN-GA), and (2) the Tobit regression approach in determining the credit risk of local government units in Croatia. The evaluation of credit risk and prediction of debtor bankruptcy have long been regarded as an important topic in accounting and finance literature. In this research, credit risk is modelled under a regression approach unlike typical credit risk analysis, which is generally viewed as a classification problem. Namely, a standard evaluation of credit risk is not possible due to a lack of bankruptcy data. Thus, the credit risk of a local unit is approximated using the ratio of outstanding liabilities maturing in a given year to total expenditure of the local unit in the same period. The results indicate that the ANN-GA hybrid approach performs significantly better than the Tobit model by providing a significantly smaller average mean squared error. This work is beneficial to researchers and the government in evaluating a local government unit's credit score.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.