Applying Adaptive Neuro-fuzzy Inference System (ANFIS) while Analysing Interdependecies of Tax Burden and Capital Structure of Croatian Hotel Companies

Various conducted studies incorporate the effect taxation has on company's financial policy, in particular in terms of the effect that corporate profit tax has on capital structure. This paper focuses on the effect the overall tax burden has on capital structure (sources of funding) of Croatian hotel companies, due to the fact that tourism as an economy branch has great impact on total Croatian GDP. Total tax burden encompasses corporate profit tax and income tax of hotel companies. In the narrow context, the problem also refers to adjustments, in terms of preferences for capital budgeting methods (new way of capital funding, corporate management, profit payment policy and bank - company relations), as well as to solvency and capital structures which banks require, as parts of contemporary concepts and views on corporate finances. The broader context, apart from GDP growth and rational planning of budget by the current government, refers to financial and market friction. Adaptive neuro-fuzzy inference system (ANFIS), as a type of neuro network based on Takagi-Sugeno fuzzy inference system, has been used in this research as an analysis tool to observe the relations, i.e. impacts, rather than as a universal estimator or optimizor.