In this article in order manage the risk from the lack of tax compliance. The optimal model “ selection forvat audit” using data mining techniques (vector machine and decision tree) be studied. In the selection for auditing, the important issue is select the right files for auditing from within the range of potential candidates. So that’ s the choice while covering the maximum tax risk, it will increase the efficiency of the tax system. because of the limits available in time and sources, Audit all tax payer will get various costs. In addition, the costs associated with the audit and the revenue from auditing are also raised. therefore, the output of the tax audit process greatly contributes depending on the quality of the selection of the audited tax payers collection. To do this research in it all, using the Delphi method, factors affecting tax risk are identified and continuing with the using of the statistical samples of research. Which includes 281 companies that were subject to Vat audit between 2001 to 2015, Different models were extracted and their ability was evaluated to choose optimally for Vat audit. The results of the study show that the Linear support vector machine method up to 70% of tax payers with this clustering algorithm correctly they will be separated depending on the analysis of existing data. Which is more reliaboh le then other data mining techniques of decision tree.

In the VAT Acts in order to control gasoline consumption as one of the environment- polluting and also to earn revenue resources for environment protection, higher tax rate than the standard rate is levied on its consumption. In this paper, forecasting income receivable from the tax base using the two-stage approach has been considered. In the first stage, tax base (gasoline consumption expenditure) has been forecasted in the period 2013 to 2016 and then gasoline consumption tax, using multiplying the tax rates in gasoline consumption expenditure predicted, has been calculated for the mentioned period. In this regard, for precise prediction of the tax revenue, supervised neural networks method and for networks training, error backpropagation algorithm are used. The results indicate that during the mentioned period gasoline price changes (as the most effective variable) arising from VAT will have no serious impact on gasoline consumption. Also, VAT revenue of gasoline consumption will increase by an average annual rate of 35 %.

Tax on value added is a kind of indirect tax which yields high income for governments. Thus, governments intend to increase it. However, raising tax rate uniformly across all goods consumed by different income groups have been criticized for being regressive and unjust. In this paper, we have used two different tax rates to distinguish luxury goods from other essential goods. Taking Justice and equity into account while levying taxes, this study shows that optimum tax rates on essential goods such as food and non-essential luxury goods are estimated to be 8 percent and 26 percent respectively. This finding, however, does not mean that tax authority should change the tax structure immediately disregarding its impacts, and tension it may create, but rather it proposes a gradual and planned system of taxes, taking precautionary measures.

Taxes make up the bulk of any government revenue and provide a sustainable source of revenue. In recent years, the main focus of the tax reform program, in almost all countries of the world, has been on VAT. But a major problem in the effective implementation of VAT, which is a nascent tax base in countries, is the phenomenon of tax evasion. Therefore, one of the most basic steps in preventing tax evasion in the field of VAT is to accurately identify tax interactions between taxpayers and the tax organization based on existing variables and laws. Therefore, in this study, for the first time, the phenomenon of tax evasion in the field of VAT is modeled using the game theory tool and based on the Korchen model in the field of income tax, and is analyzed based on the interactions between taxpayers and the tax organization. The results obtained by mathematical analysis of the developed models indicate that with the integration of VAT audit and Income tax audit, the rate of tax evasion in the field of VAT will be reduced.

Tax incidence is a key question in empirical public finance and tax policy design. Using monthly price data from April 2005 to March 2014 in Iran, we classify 43 commodities to exempt and taxable groups. By comparing monthly price changes for the two categories over the periods with tax rate changes, we employ a difference-in-differences strategy to estimate VAT incidence. Consumer share of VAT is estimated to be 63 percent. However, this point estimate should be interpreted with caution because the 95 percent confidence interval is large and contains both full and less than complete pass through. No pass through is rejected at 5 percent significance level. Lack of precision in estimates could be a result of small tax increases and high inflation rates during this period.

The main reason for focusing on value added tax (VAT) is expanding tax base and increasing tax revenues. Regarding the implementation of VAT Act initiated in October 2008, this paper attempts to estimate tax revenue resulting from this Act, which is based on input ! output table and production method.Based on the results of this research, VAT base according to the Act is about 44 percent of GDP; with regard to the rate of 1.5 percent, potential VAT revenue will be 0.67 percent of GDP.Results of this study show that the full implementation of VAT act with rate of 1.5 percent will not have significant effect on reducing the operating budget deficit. The VAT rate should be increased in order to makeup such a deficit.

Value Added Tax (VAT) as a method of tax charging with creating a new broad tax base has been interest of many countries. Also value added tax in our country in order to reform the structure of tax and increasing government revenues was approved by the parlemant after a relatively long time and in the second quiartor of year 1387 was carried out. Given that this law was carried out, as an experiment law and for five years study of effects of this tax on macroeconomic variables is very important. In this study has tried to use the analytical relationships Input-Output and production of technical coefficient matrix constant assumption of fixed economic conditions and economic variables and limiting assumptions of this study to the price effects resulting from applying VAT on cost of whole different departments to deal with the country's economy. By using of model price of input-output and applying tax rates issue of Article 12 on exemption for goods and services and ultimately applying export exemption issue of article 13 on value added tax the price effects of each section of economy is calculated and with considering of share of each section from the whole output the price effects is calculated. Results show that implimantion of VAT has had very low price effects.