Journal of Tax Research

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

---

Taxable capacity is an economic capacity of a given country, the extent to which taxpayers can tolerate the burden of all types of taxes (i.e. the degree to which taxes could be paid). Taxable capacity is difficult to estimate. The related important issue is to review how tax revenue as a part of state revenue is increased. To achieve this objective, a precise estimation and recognition of current resources are necessary. Appropriate criteria for calculating taxable capacity is the tax bases of the different economic sectors, so value added of sectors is also calculated. In this study, modelling of neural network is applied in which independent variables enters neural network learning system as an input layer. The input variables of the model including inflation rate, Gini coefficient, the ratio of the urban population to the total population, the degree of economic openness and value added share of agriculture and industry sectors as a percent of GDP , these are dependent variables of the model and taxable capacity is dependent variable which is regarded as output layer in neural network. Neural network is appropriately selected according to the trial and error method for the hidden layers and each layer's nodes. In this learning model, intra network method( batch) and multi perceptron layer approach( MPL) have been used as progressive and feedback.

Keywords: Taxable capacity, Tax ratio, Gross Domestic Product(GDP), Dummy variable, Nueral network

Full-Text [PDF 712 kb]   (2159 Downloads)    

Add your comments about this article : Your username or Email:

---