جستجوی مقالات مرتبط با کلیدواژه "keywords" در نشریات گروه "اقتصاد"

Today, due to economic volatility, the topic of stock price forecasting and investment risk has particular importance to stock traders. Recently, fuzzy logic has been used to model dynamically candle stick in order to stock trading analysis and predicting investment risk in stock trading but it has the challenge of sensitivity to the number of non-useful stock trading samples and the inappropriate tuning of membership functions designed for candlesticks patterns. In this paper, we propose the regression method based on radial basis function as a pre-processing step to reduce the insignificant stock trading samples and then we use the particle swarm optimization method to adjust the values of fuzzy membership functions of the candlestick patterns optimally. The jaya and firefly particle swarm based are able to optimize fuzzy membership functions of candlestick patterns robustly. The results of the proposed method on top iranian stocks trading companies show best performance of the proposed method.

 The lack of certainty in the movement of the stock market has made forecasting a challenging task in the field of financial time series forecasting. On the other hand, it is not easy to analyze the time series data of stock prices due to non-linearity and high noise. Therefore, the aim of this research is to predict the long-term and short-term trend of the capital market. To achieve this goal, artificial intelligence algorithms of particles and genetics have been used in a comparative manner. The studied variable is the total stock price index in Tehran Stock Exchange in the period of 2016 to 2021 and on a monthly basis. The data have been reviewed after collection using the smoothing method for holidays, and in order to increase the accuracy of the models, the optimal window length of each algorithm has been calculated. The findings indicate that the genetic algorithm by minimizing the prediction error is a suitable algorithm for predicting the short-term and long-term trend of the total price index compared to the particle algorithm in the studied time period.

The purpose of this article is to investigate the impact of political risk on the shadow economy. To this end, using data from 52 developing countries and 38 developed countries, it investigated the effect of political risk on the size of the underground economy over the period 2000-2020. In this study, the quantize panel approach was used separately for two groups of developed and developing countries to estimate the research model. The results show that political risk had a positive and significant effect on the size of the underground economy in all decades and in both developed and developing country groups. This means that countries facing higher political risks have a more hidden and informal economy. Also, the results of this research show that the unemployment rates, abundance of natural resources and taxes have a positive effect on the size of the shadow economy, but the quality of regulations and economic freedom significantly reduce the size of the shadow economy in both groups of countries. Based on the results, reducing political risks, improving government regulations in support of the private sector, improving business and trade freedom, financial and operational transparency in the exploitation of natural resources, as well as creating jobs and improving the business environment are policy recommendations of this study.

The aim of this research is to examine the efficiency of stochastic differential equation models in predicting stock prices. To evaluate the accuracy of these models, a comparative study has been conducted between these models and conventional time series models. In this domain, Geometric Brownian Motion and Heston models have been reviewed. For this study, the shares of Mellat Bank with the ticker symbol ‘VBMELLAT’ listed on the Tehran Stock Exchange have been examined as a case study; for this purpose, the study has been conducted on the price data of these shares from the beginning of 2015 to the beginning of 2023. Before modeling the stock, price and making predictions, the possibility of recurring patterns and self-similarity in the price movement trend has been examined. The results indicate that Mellat Bank’s shares have long-term memory, which makes it somewhat possible to predict their behavior. Subsequently, the stock price prediction for the ‘VBMELLAT’ ticker symbol has been carried out, and the research findings show that the Heston stochastic differential model, based on most post-test evaluation criteria, performs better in predicting stock prices; such that this model only showed a 0.0464 percent absolute error in predictions. The AR time series model also performed acceptably with the key assumption that past patterns will repeat in the future. This assumption is consistent with the presence of long-term memory and stability in the overall index, which places the AR model second in the evaluation criteria after the Heston model. According to the results obtained, stochastic differential equation models are efficient models for modeling and predicting stock prices.