Since the outbreak of the financial crisis, the major global credit rating agencies have implemented significant changes to their methodologies to assess the sovereign credit risk. Therefore, bond rating prediction has become an interesting potential for investors and financial institutions. Previous research studies in this field have applied traditional statistical methods to develop models which provide prediction accuracy. However, no overall distinguished methods have been used in predicting bond ratings. Moreover, recent studies have suggested ensembles of classifiers that may be used in bond rating prediction. This article proposes an improved machine learning aimed to predict the rating of financial bonds. We empirically compare the classifiers ranging from logistic regression and discriminant analysis to nonparametric classifiers, such as support vector machine, neural networks, the cost-sensitive decision tree algorithm and deep neural networks. Three real-world bond rating data sets were selected to check the effectiveness and the viability of the set of the classifiers. The experimental results confirm that data mining methods can represent an alternative to the traditional prediction models of bond rating.

Purpose: The purpose of this paper is to evaluate the impact of corruption on the environmental quality in Tunisia. Indeed, the post-revolution period is characterized by a remarkable increase in the rates of corruption.Design/methodology/approach: The direct and indirect effects of control corruption on economic growth and CO₂emissions in Tunisia have been examined using the autoregressive distributed lag (ARDL) cointegration framework among corruption, growth and CO₂emissions.Findings: Results substantiate a positive and significant relationship between control of corruption and economic growth, a negative and significant relationship between control of corruption and environmental quality (CO₂) and a negative and significant relationship between control of corruption and energy consumption. The findings suggest that while the control of corruption contributes to economic growth, its positive effect could be transposed indirectly via its impacts on environmental quality.Originality/value: A strategy against corruption will reduce CO₂emissions; however, its positive effect on economic growth indirectly contributes to reverse this relationship.

Tourism is viewed increasingly as an essential sector to local, regional and national reconstruction and development for economies at various scales. However, its contribution on environmental quality degradation is more important. Indeed, any increase in the number of tourism requires amounts of growing energy, which increases CO2 emissions. The objective of this article is to empirically investigate the relationship between tourism development, energy consumption and carbon emissions in Tunisia over the period of 1974-2014.To recognize this relationship, a bonds test of co-integration, ARDL model and Granger Causality Tests have been employed. After having confirmed that the existence of co-integration relationship between energy consumption tourism demand and CO2 emission, the results indicate that tourism has a direct impact and statistically significant effect on the consumption of energy for the future of the Tunisian economy. The short-term results indicate bidirectional causality between energy consumption and emissions of CO2 and also between the consumption of energy and tourism, meanwhile the absence of any causal relationship between the emissions of CO2 and tourism. Tourism affects the quality of the environment indirectly through the consumption of energy. So, the protection measures in the tourism sector should be laid down in Tunisia. Sustainability in the tourism sector is one of the major axis of debate on tourism development integrated in the environment.