حسین کیانی زاده

Forecasting the stock price due to its attractiveness has always been on the focus of experts and capital market activists. In such a way that various prediction models such as technical and fundamental analysis and data mining are increasingly used to predict stock prices. Past studies indicate the possibility of stock price prediction by machine learning models, but the prediction accuracy of these models has not been evaluated. The purpose of this research is to accurately compare the intelligence of five commonly used data mining algorithms, including neural network, Logestic regression, k-nearest neighbors, support vector machines and cross validation. Among the 385 active companies in Tehran Stock Exchange, 72 companies have been selected by the method of systematic elimination and the above models have been implemented to predict stock prices on the daily prices of selected stocks for the years 2009 to 2020. The stock price is used as a dependent variable and changes in the opening price, closing price, highest price, lowest price and volume of trade, daily price of forign currency, gold and oil price are used as independent variables. Three indicators R2, MSE and RMSE are used, to evaluate the accuracy of models, and analysis of variance using F statistics is used to fit the accuracy of the models, and t-student statistic is used to compare two models. The results are showed that among the smart algorithms used, the support vector machine algorithm has the highest accuracy. Matlab software is used to analyze the data and compare the models.

The capital market is growing rapidly. This has led to higher demand for information, more effort to predict and invent new models for predicting the future of the market. Predictive models can be classified into three categories. The first group uses technical analysis, the second group uses fundamental analysis, and the third group uses data mining and machine learning. In the present study focusing on data mining method to compare the accuracy of selected machine learning models including neural network, logistic regression, k nearest neighborhod, support vector machine and cross validation to predict stock prices for 12 selected companies of Tehran Stock Exchange that They have been selected through systematic deletion method in the form of machine learning models and the results of this paper showed that among the machine learning algorithms, the support vector machine algorithm has the highest predictive power in stock prices.Keywords: stock exchange, forecast; Stock prices, algorithms, machine learningJEL Classification Code: C8, G1

Money laundering is defined as the act of altering or transferring a property for the purpose of concealing its illegal origin, or assisting one who commits it. Some of the difficulties that this may create for the economy are: disturbance in the large – scale policy making of the country, undermining the private sector, hindering the process of privatization, increasing inflation, weakening the integrity of financial markets, increasing the credit risks, disrupting the long-term export and import investments, encouraging clandestine operations, facilitating profit making in criminal activities, and finally escalating the government, s expenses and the flight of capital. The causes for this in Iran are economic corruption, smuggled goods and drugs and lack of sufficient supervision over tax-collecting system. To examine the negative effects of money laundering on the economic growth in Iran, the Solow - Swan growth model has been adopted. The negative sign in the variables of logcrime 1 (embezzlement, graft, forgery) and logcrime 2 (discovery of smuggled drugs) confirms the negative relation between money laundering and economic growth.