عبدالمجید عبدالباقی عطاءآبادی

In this paper, the European option pricing is done using neural networks in the Black-Scholes-Vasicek market. The general purpose of this research is to compare the accuracy of neural network and Black-Scholes-Vasicek models for the pricing of call options. In the sequel, the finite difference method is applied to find approximate solutions of partial differential equation related to option pricing in the considered market. In the design of the artificial neural network required for this research, the parameters of the Black-Scholes-Vasicek model have been used as network inputs, as well as 720 data from the daily price of stock options available in the Tehran Stock Exchange market (in 1400) as the network output. The approximate solutions obtained in this article, which were carried out by two methods of neural networks and finite differences on the Tehran stock exchange based on the daily price of stock options, are shown that neural networks are more accurate method comparing with finite difference. The comparison of pricing results using neural networks with real prices in the assumed market is presented and shown via diagram, as well. In this paper, the European option pricing is done using neural networks in the Black-Scholes-Vasicek market. The general purpose of this research is to compare the accuracy of neural network and Black-Scholes-Vasicek models for the pricing of call options. In the sequel, the finite difference method is applied to find approximate solutions of partial differential equation related to option pricing in the considered market. In the design of the artificial neural network required for this research, the parameters of the Black-Scholes-Vasicek model have been used as network inputs, as well as 720 data from the daily price of stock options available in the Tehran Stock Exchange market (in 1400) as the network output. The approximate solutions obtained in this article, which were carried out by two methods of neural networks and finite differences on the Tehran stock exchange based on the daily price of stock options, are shown that neural networks are more accurate method comparing with finite difference. The comparison of pricing results using neural networks with real prices in the assumed market is presented and shown via diagram, as well.

In this article, the pricing of option contracts is discussed using the Mikhailov and Nogel model and the artificial neural network method. The purpose of this research is to investigate and compare the performance of various types of activator functions available in artificial neural networks for the pricing of option contracts. The Mikhailov and Nogel model is the same model that is dependent on time. In the design of the artificial neural network required for this research, the parameters of the Mikhailov and Nogel model have been used as network inputs, as well as 700 data from the daily price of stock options available in the Tehran Stock Exchange market (in 2021) as the net-work output. The first 600 data are considered for learning and the remaining data for comparison and conclusion. At first, the pricing is done with 4 commonly used activator functions, and then the results of each are com-pared with the real prices of the Tehran Stock Exchange to determine which item provides a more accurate forecast. The results obtained from this re-search show that among the activator functions available in this research, the ReLU activator function performs better than other activator functions.

Financial markets are currently experiencing sharp volatility. Studying how the returns and volatility in one market affect other markets has always been one issue that helps investors and policymakers to make optimal decisions. Given the importance of volatility spillovers in the Iranian financial market, this study aimed to investigate the mechanisms behind the volatility spillovers in the foreign exchange, gold, and stock markets to the oil market in Iran. This descriptive study was conducted using the daily and monthly data from the oil, foreign exchange, gold, and capital markets from 2010 to 2019 and to analyze the data, ARCH and GARCH models have been used. The results of this study showed that the abnormal volatility of the foreign exchange and gold in the previous day positively affects the abnormal volatility of the oil market today, this indicates that money flows in the currency market, spilling over the fluctuations into the oil market. hey also found that the abnormal volatility of the capital market in the previous day negative affects the abnormal volatility of the oil market today, indicating that if money flows in the capital market, which indicates the flow of money in the capital market from yesterday, increasing the transfer of emotions to the current capital market but does not spillover into the oil market and volatility is not transferred into the oil market. Overall, the findings of this study confirmed the positive impact of the foreign exchange and gold markets on the abnormal volatility in the oil market in the short term (daily) and long term (monthly), but did not confirm the positive impact of the capital market on the abnormal volatility in the oil market.

This study was conducted to determine the stock portfolio with the best return and low-risk investments using momentum-contrarian strategies (MCSs). The momentum-Contrarian strategy is one of the well-known models to construct the portfolio which suggests buying the stocks with the best performance (the winner stocks) and selling the stocks with the worst performance (the loser stocks). The optimal values of the portfolio's objective function and the weight of all assets in the portfolio that are not necessarily the same are calculated by defining a nonlinear multivariate optimization model combined with momentum-contrarian strategies (MCSs). The return information of companies listed on the Tehran Stock Exchange from 2014 to 2019 was used to select the best optimal portfolio. The results confirmed the stability in the profitability of the contrarian optimal portfolio with minimum risk compared to other optimal portfolios. Furthermore, through MATLAB software the optimal weight of assets in the optimal portfolio is calculated based on statistical data.

In this paper, we use fuzzy numbers and possibility theory to model possibility. The purpose of this work is to determine the optimal investment model based on the neural network method for fuzzy LR, trapezoidal and triangular numbers in an optimal portfolio. It is listed on the Tehran Stock Exchange to maximize "returns" and reduce "risk" to find the optimal portfolio. Therefore, to achieve this goal, the problem of multi-objective nonlinear programming is addressed. Also, by substituting the mean-variance model and the standard mean deviation instead of the Markowitz mean-variance model, the selection of the optimal portfolio in the possible space is examined. Finally, after calculating the model of the possibility of fuzzy numbers, we reach the optimal stock portfolio, which can be used to set the stock portfolio that has the highest returns and the lowest risk.

This study examines trading strategies based on trading systems by analyzing the performance of 11 technical indicators. The data used for analysis were financial data of all firms listed on the Teh-ran Stock Exchange in the period from 2010 to 2020. Excluding the firms whose data were not available for the period under study, 135 firms were selected as the research sample. The results showed that the signals containing three indicators of moving average, exponential moving average, and relative strength over a weekly up to six-month period to buy or sell stocks (as a strategy) could be used more confidently compared to other indicators to achieve higher returns and profitability. As a result, investors can use the signals that these three indicators in weekly (EMA) and monthly (MA, RSI) periods and the quarterly (MA) and six-month (RSI, EMA) periods to determine buying and selling strategies with the lowest investment risks. It is also recommended that investors use a combination of these three indicators to invest, and extend their investment period over a longer period of time to bear less risk, and more returns.

Traders in the capital market always seek methods to make full use of available information and combine them to find the best buying and selling strategy. The present study uses a linear hybrid system to combine 106 signals from moving averages oscillators and RSI signals in the technical analysis along with two buy and sell bonds. In addition, the system has correctional property and modifies its parameters over time and according to new information. The result of the research on the Tehran Exchange overall index in the period 1380 to 1397 indicates that the system after the optimal training on training data has an average of daily returns of 0/0025, 0/0048 risk, and a daily Sharp ratio of 0/52, which is better than the individual performance of each signal and market performance in daily average return and sharp ratio criterion.

In this paper a combination of two financial derivatives in financial markets modelled of future interest rates is presented and evaluated. In fact European option pricing is driven when zero-coupon bond is considered as underlying asset in a market under Hull-White model . For this purpose, the exact solutions of the valuation of this bond option are driven, using Lie group symmetries method. Then in the next part, the finite difference method is applied to find numerical solutions for assumed bond option pricing. Then the significance and usefulness of this approximated method is comparing with the exact solutions by some plotted graphs.