جستجوی مقالات مرتبط با کلیدواژه « بازار طلا » در نشریات گروه « مالی »

In recent years, deep learning neural networks have been recognized as powerful tools for solving complex problems. Deep learning is a subfield of artificial intelligence in which complex problems with numerous parameters and inputs are modeled based on a set of algorithms. In this research, a new framework of deep learning is presented. Using wavelet transform, stacked auto-encoders, and the Long Short-Term Memory or LSTM, we predict the market direction in the future contracts of gold coins of Iran's Commodity Exchange market. The input data is first denoised using the wavelet transformer in the proposed method. Then, using the stacked auto-encoder, the indicators influencing the market direction are identified. Ultimately, these indicators are given as input to the LSTM architecture to predict the market direction. Proposing several new technical indicators to increase the accuracy of the proposed model, adjusting the parameters of the utilized algorithms, including LSTM, for this problem, and suggesting a trading strategy to achieve appropriate profitability are among the contributions of the present study. Investigations reveal that the proposed method outperforms other approaches and achieves higher accuracy and efficiency.

Inferring and inducing among the relations for many of the phenomenas is common in most of sciences. Accordingly, econophysics experts are trying to fill the gap between microeconomics and macroeconomics to explain complex financial systems, using the statistical physics tools. Using a dynamic econometric model, the impact of exchange and gold markets shocks on the stock market is studied. The results show the more significant contribution of the foreign exchange market shocks than the gold market shocks on the fluctuations of stock market. Furthermore, this study forms an assumptive portfolio consisting of three assets including stock, exchange and gold and use random portfolio theory to analyze the risks and uncertainty. The level of uncertainty and risk is studied by using the characteristics of the Castaing, Gagne & Hopfinger distribution functions. The results indicate a high level of uncertainty and risk in the macroeconomic assets portfolio. In other words, the occurrence of financial crises in these markets is expected.

In the current era, the study of the relationship between different markets and their impact on each other has become a necessity micro and macro investors. By investigating the relationship between markets, in addition to being able to obtain the required information about the impact of the markets, it can also help him in identifying various risks. According to the importance of the subject, in this paper, we have tried to investigate the relationship between the oil market and the gold, dollar markets, companies and energy funds in the field of energy, using the new associative rules approach and the Apriori algorithm. The use of associative rules explicitly explains the relationships between database fields and the relationships and interrelationships between a large set of data items. The results of this study indicate a direct relationship between the oil market and companies active in the energy sector, and the reverse relationship with the dollar index. There was also no significant relationship between the oil and gold market.