genetic algorithms

In recent years the use of artificial intelligence techniques in the financial and investment markets instead of customary quantitative methods has been increasing and gives better performance towards classic methods usually. Artificial Neural Network (ANN), has weaknesses points despite its enormous benefits also. In this study, in order to overcome the weaknesses of the network consists of combining artificial intelligence methods with Evolutionary algorithms, means of artificial neural network combined with genetic algorithm (GA) and Particle Swarm algorithm (PSO) to model and daily predict of nominal exchange rates or the exchange rate dollar by Rial in Iran in the period 21.03.2013 to 22.12.2019 is used. This combined model with neural networks method as one artificial intelligence model according to the criteria of MSE , RMSE, MAE, U.Theil compared. The results of this research show the superiority of synthetic neural network model -Particle Swarm algorithm compare to other models of investigation.

This paper is aimed to compare stock index forecasting using hybrid models based on Genetic Algorithm (GA) and Harmonic Search (HS) with Artificial Neural Network (ANN). The most relevant technical indicators as inputs and the optimal number of neurons in hidden layer of Artificial Neural Network designated by metaheuristics including Genetic Algorithms and Harmony Search. Daily price index of Tehran Stock Exchange from 21 December 2012 to 21 December 2015 applied to predict and test stock index. The accuracy of forecasting of three models including Regular Artificial Neural Network model, hybrid neural networks based on GA and hybrid neural networks based on HS is evaluated by the prediction error. The results show that the accuracy of prediction in Metaheuristics models such as Genetic Algorithms and Harmony Search in the test period is higher than normal Artificial Neural Network. Also prediction by hybrid neural network model based on harmony Search during the test period compared to hybrid Artificial Neural Network model based on Genetic Algorithm is more accurate.

Ongoing sanctions on Iranian economy have proved to be very harmful and detrimental to Iranian economic affairs and social welfare. Evaluating the unfair impacts of these sanctions on Gross Domestic Product (GDP) and social welfare is the aim of this paper. Firstly, we have developed a generalized growth model in the presence of sanctions while treating exchange rate as a random variable. Secondly, three different forms of sanctions are introduced into the model and their bearings on national product and social welfare is studied. The first tier of the sanctions is imposed on consumption, intermediary and capital goods while exchange rate is assumed to have a random behavior. Then sanctions are also imposed on Iranian oil and gas production. We have devised several scenarios using stochastic Hamilton Bellman Jacobian value function (SHBJ) and genetic algorithm optimization methods. Our results of the first and second scenario imply that the level of social welfare is mostly affected by oil and gas sanctions while goods embargo has targeted goods production. The effects of sanctions on GDP and social welfare is represented by a concave curve. This curvature shows that the impact of sanctions on GDP and social welfare is stronger at the beginning than later on when further sanctions are introduced. In the third scenario oil, gas and goods sanctions are imposed simultaneously. Our results also show that the third scenario effects is stronger than the other two. According to the Gross Domestic Product data acquired for year 1390, oil and gas sanctions have lowered the GDP by 30 percent, while the overall reduction in GDP through all sanction collectively is estimated between 30 to 50 Percent.

In order to estimate the production function besides productivity and economic growth, the time series of capital stock is required. Time-series that available for capital stock is not so reliable because of Variations in suggested methods and also difficulty in the calculation of this variable. The continuously inventory method (CIM) has been more attention, among the existing methods. We improve CIM in this research. For estimating the capital stock we developed an algorithm and titled that “Programming or Recursive Algorithm”.The following can be noted in capabilities of the model that developed in this study. Unlike the previous studies we taking the variable depreciation rate of capital in different periods, considering the quality variable of war and its impact on the rate of depreciation, investigation of nonlinear and linear production function in order to increase estimation accuracy and considering energy as well as labor and capital input.The results show that compared to the time series reported by the Central Bank of Iran, the series calculated in this study are similar trend, but with some differences.The mean of depreciation rate has been calculated 5.1% for the period 2009 to 2010. The estimation results show that in war period we have always higher depreciation rate than average rate of depreciation in period of this study.

In this study، the electrical energy consumption in Tehran before reduction subsidies and after targeting subsidies was examined with using a dataset collected from household subscribers Tehran Electricity Distribution Company from August 2000 to November 2012. After review and analysis values، a model was proposed for predicting power consumption. The proposed model was a combination of trigonometric coefficients and power factors. The best values were obtained by using a genetic algorithm. Procedure of electrical energy consumption in Tehran after Implementation of subsidies reduction plan was compared with the predicted model of electrical energy consumption in Tehran before Implementation that plan. The results indicated that implementation of subsidies reduction plan reduced electrical consumption growth rates and also a little reduced consumption rate. The other results of this study contain consumption patterns in order to manage the future consumption level of electrical consumers in Tehran. Also the results showed that، because demand for electricity is inelastic to price and income in the short time، as a result price policies cannot be effective in controlling the electricity demand، then should use non-price and intensive policies to reduce the consumption of electricity.

The main goal of this paper is to estimate the elasticity of substitution between energy and other factors of production by using a multi-stage CES production function. In order to achieve this goal، we design a nested CES production function with four inputs، labor، capital، energy and investment in research and development for Iranian economy. This nonlinear production function is estimated by continuous genetic algorithms method. This method is relatively more efficient than traditional econometrics approach. In the first stage، three different functions are estimated and the best one is selected. In the next stage، we have calculated the elasticity of substitution between energy and other inputs of production. Our choice of nonlinear production function، the explanatory variables، and also the estimation method make this research different from those already done for Iran. The results indicate that one percent increase in labor force reduces energy consumption by 0. 56 percent. We also find that one percent increase in physical capital decreases energy use by 0. 59 percent، and similarly one percent increase in investment in R&D (Research and Development) might reduce energy consumption by 0. 46 percent. Furthermore، we calculate marginal products of different input for various years and observe that the marginal product of labor has increased after Iran-Iraq imposed war. Moreover the marginal product of energy has increased since 1995. This might be a result of energy saving policy implemented in Iran after this year.

The main purpose of this study is to develop a model for determining the optimal shares of renewable and non-renewable sources of energy in a sustainable growth model. We develop an optimal control model in which nonrenewable and renewable sources of energy are inputs of production. The model allows us to determine the optimal shares of renewable and nonrenewable energy inputs. Finally، we use the model to determine these shares for Iran. Genetic algorithms technique is used to estimate the coefficient for production and utility functions. We also estimate the pollution equation. Using these parameters، we derive the optimal paths for consumption، output and renewable and nonrenewable energy shares in Iran. The results show that the optimal share of renewable energy in total energy consumption is about 0. 8 percent in 2010. While the actual share of renewable energy in Iran was 0. 4 percent. Moreover، our model predicts this share should rise to 2. 1 percent of total energy consumption by 2021 to be able to stay on sustainable growth path. This requires an average growth rate of 26 percent in renewable energy production each year.

Exchange Rate uncertainty means an unpredictable change in the exchange rate that can cause a great impact on other economic variables and institutions such as banks and credit institutions especially in developing countries. In this study, using monthly data from the 2009/3- 2013/9, the effect of recent exchange rate crisis on Iranian banks and financial institutions is estimated and predicted. To do that, models such as VAR, VECM, Genetic and PSO Algorithm are employed. The results of estimating the VAR model indicates that there is a negative relationship between exchange rate volatility and stock market returns. Further, Co-integration test results imply the existence of an indirect long-run relationship between these two variables. By simulation of linearly and exponentially models using Genetic and PSO algorithms to compare the accuracy of these models with estimated VAR model, it was determined that VAR model can predict more accurately. Prediction results showed that persistence of exchange rate fluctuation can lead to first a diminishing increase followed by reduction in the index. However, reduction of exchange rate can lead to an increase in financial and credit institution's stock index.

Generally, investors consider simultaneously conflicting objectives such as rate of return, risk and liquidity in portfolio selection. On the other hand, every investor has his own specific preferences about objectives. Therefore, we can use Multi Objective Decion Making (MODM) techniques in order to solve portfolio selection problem. The Studies shows that a MODM technique by nonlinear goals such as minimization of nonsystematic risk and skewness maximization isn’t employed for portfolio selection, so a new approach is applied. We employ MODM model to select a best portfolio in 50 superior companies in Tehran stock exchange with regards to optimization objectives of return, systematic risk, nonsystematic risk, skewness, liquidity and sharp ratio. This model is non-convexed, so operational research algorithms can not find the best solution; therefore we use Genetic Algorithms (GA) for achieving nonlinear multi-objective model. In the end, the result of GA is comprised with Markwitz classic model and goal programming (containing linear and nonlinear objectives). The comparison indicates that although return of the portfolio of GA model is less than the other models, but GA has the best results in decreasing risk criteria which completely cover the return and lead to best results. The other advantage of using GA is a higher diversification in its proposed portfolio in comparison with other models.

Selecting a portfolio is one of the most critical issues in investment. In this process, the investor faces numerous alternatives and he must choose the most optimized one. Determining which shares are most suitable to be put in the portfolio and capital allocation between them, are complex issues. Theoretically, assuming constant return, we can minimize the risk by applying a quadratic equation, but experimentally and with respect to the Diverse investing tools and different investor's utility functions, the mathematical approach for solving this model requires vast calculation and planning. The main object of this research is applying genetic optimization algorithm in selecting a portfolio from Tehran Stock Exchange, listed companies, In away that the chosen portfolio minimize the investment risk while maximizing the return. In order to do this, we choose 40 companies shares from the population. After calculating the main variables – monthly risk and return for an eight year period- and preparing the required algorithm, the results are compared with Markowitz and the Random choice models ones in different levels of portfolio and with respect to hypotheses. Relevant statistical tests on 1st and 2nd hypotheses showed a meaningful difference; furthermore the genetic algorithm results defeated the Markowitz and the Random choice models.