firefly algorithm

Banks face credit risk in the process of providing facilities based on the amount of resources provided. In the meantime, facility portfolio management can be effective in reducing credit risk by optimally allocating resources to economic sectors. In this research, the portfolio of Sina Bank's facilities is determined by using the Markowitz modern portfolio model and meta-heuristic algorithms of genetics and firefly. Comparing the performance of the models indicates the greatest efficiency of the genetic algorithm model in optimizing the bank's facilities portfolio. the results of the estimation of this model show that the service & commercial, housing & construction sectors have the largest share in the optimal portfolio of the bank's facilities. Industry & mining, agriculture & water sectors are considered risky assets of Sina Bank. the process of granting facilities has not been optimal. To reduce the credit risk of that bank's facilities, 52.4% should be allocated to the service & commercial sector, 40.7% to the housing & construction sector, 3.5% to the industry & mining sector, 3.4% to be allocated to agriculture & water sector.

The main goal of investing in the stock market is to get the highest return at the desired time. Successful trading in financial markets should be done close to key reversal points.In this research, we are trying to select the widely used technical rules by studying the previous researches and improving the decision parameters in the mentioned technical rules for each stock by using the firefly and gray wolf algorithm and converting contradictory signals issued from the optimized indicators to the unit. And finally, through the LSTM neural network, we will try to predict the entry and exit positions of the stock market.This research was conducted from 1390 to September 1401 on Tehran Stock Exchange companies. The proposed model has been able to correctly identify buy, sell and hold points for a future trading day for long-term investors with an error of about thirty-six percent.Keywords: Technical indicators, firefly algorithm, GWO and LSTM

Choosing a stock portfolio is one of the important topics in the field of investment management, which discusses how to allocate an investor's capital to different assets and form an efficient portfolio, which depends on the assumptions and modeling conditions for selecting and optimizing the investment portfolio. It is closer to real world conditions, the results will be more reliable. Considering a single period horizon for investment is not very realistic and most investors invest for more than one period so that the investor can review his position over time .Various patterns and methods have been presented since Markowitz's initial work to choose the optimal investment portfolio. However, finding the most useful pattern in choosing this portfolio has always been a concern of investors. In this research, a number of stock portfolio optimization algorithms such as ant algorithm, genetic algorithm, cultural algorithm, particle swarm algorithm, and firefly algorithm are given. Which is briefly explained about each.

The main goal of investors in the stock market is to get the highest return at the desired time, therefore introducing the most suitable method for conducting transactions is of special importance for investors. Successful trading in financial markets should be done close to key reversal points. In recent years, various systems have been developed to identify these return points. Technical analysis tries to identify the time to enter and exit trades.In this article, we are trying to select the one with a higher success rate by using the technical rules according to the previous researches, and by using soft calculations, the decision parameters in the technical rules are improved using the firefly algorithm.The results of this model are compared with the results of using the standard parameters of the indicators and the results of the purchase and maintenance strategy. In order to validate the introduced trading system, we compared it with the results of the optimized intelligent system based on optics and genetic algorithm. The results of the research show that by optimizing the parameters of technical analysis indicators, the investment efficiency can be increased compared to the usual methods in the stock market and previous researches.

The type of customer service during the warranty is crucial for each complex. The purpose of customer service will be to meet the satisfaction of customers. Many components can contribute to accomplish this goal. One of the most important components is financial components. Today's world is a world of wide developments in all dimensions. The majority of companies are, more than ever, aware that the delivery of after-sales service is very effective in the loyalty and repetition of customer purchases. The intense focus on the quality of service causes the product to be valuable in terms of customers and their loyalty. Therefore, in this study, designing a credit risk management model for the for the Saipa Yadak Company and its Representatives Network using financial components of after-sales service and meta-heuristic algorithms was discussed. The sample studied in this research is the representatives of Saipa Company.The results showed that using financial components including, service cost, performance, good accounting, the amount of collateral and the amount of after-sales service agents have an impact on optimal credit risk management. Also, firefly algorithm and bee colony algorithm have the ability to predict the optimal management of credit risk using financial components.

By anticipating financial turmoil, it is possible to take the necessary precautions before financial distress occurs by managers and investors. This study compares two algorithms for prediction of bankruptcy using Artificial Neural Network (ANN) and Neural network optimized metaheuristic Firefly Algorithm (FA). To run test, first initial values are set for the network weights and biases and then during the optimization process, a population of different weights and biases is generated by FA algorithm. The conversion function used in the output layer is linear and for the middle layer a non-linear sigmoid function is selected. To conduct this research, the data of 79 companies listed on TSE during 2012 to 2015 were collected and analyzed statistically by backpropagation neural network and FA algorithms. The results show that FA, compared to ANN predicted the companies’ bankruptcy much better. Also, FA Algorithm maintains a good correlation between bankrupt and non-bankrupt companies, just like real data.

Today, natural disaster is threatening the lives of people and their assets and properties.Relief supply chain is the most agile and dynamic supply chain. Indeed, the pivotal role of relief supply chainhas been identified in responding to crises and reducing the burden on humans. In this regard, the goal of allocatingand locating issues is to allow each injured person to receive the services and goods from the distributioncenters according to demand, and suppliers will also provide goods and services for the distribution centers. Thepresent study tried to provide a mathematical model for the problem of allocating earthquake victims to existingand potential hospitals using ultra-innovative algorithms. For this purpose, first, the design of its mathematicalmodel and its innovation aimed at minimizing the costs of establishing potential hospitals, sending injured peopleand sending services and goods from suppliers to hospitals. Then, the validation and accuracy of the mathematicalmodel were evaluated using Gamz software. In the next step, acceptable results were obtained with codingin MATLAB, using fire suppression algorithms and optimizing particle swarm. After the efficiency was established,the problem test was used for the data in order to compare the algorithms. Finally, it was identified thatthe particle swarm optimization algorithm was superior to the firewall algorithm in both runtime and cost values.

Cost of capital is the minimum output rate expected by investors; this expected output rate is determined considering the risk of the company. Cost of capital refers to the cost of financing the company in order for investment or provision of working capital that consists of two parts: The cost of financing from long-term debts with interest and the cost of financing from the rights of shareholders. Cost of capital is the cost of long-term financing of the company. Companies, using debts and rights of shareholders, provide financial sources and use them in assets. In this research, using financial information of 97 company during the years of 2011 to 2017, using with help of accounting variables, it was attempted to predict cost of capital in companies listed on Tehran Stock Exchange. The results showed that there is a significant relationship between debt ratio ratios, growth opportunity, sales growth, ownership type (political relationship), fixed asset ratio, size of company with capital cost; and Vector machine regression and firefly algorithm, using the mentioned variables, has about 93 percent ability to predict cost of capital of the companies listed on Tehran Stock Exchange.

One of the reason affecting on the national economy is, GDP . But it only covers market value of final goods and services produced in the economy;it is not inclusive negative environmental impacts.On the other hand as a result of trade liberalization, economic activity expanded and use of resources and energy inappropriately increases.So theoretically, demonstrate that GDP is not a good criterion for measuring the economic well-being. Consistently, standards for calculating national income has been proposed to raising the inadequacy of these measures standards, is green GDP. In this study, to evaluate the impact of trade liberalization on green GDP, methods gravitational search algorithm and Firefly algorithm that has been used for some given time in the years 1961- 2015. The results of the evaluation of the impact of trade liberalization show that this variable is positive and significant effect on green GDP. The results show that due to the positive impact of trade liberalization on green GDP, this variable as a variable known to reduce pollution; this means that an increase in trade transactions with Iran will lead to improved environmental quality.

Fuzzy multifunctional sets reduce the need for accurate data for decision making. Data Envelopment Analysis is a theoretical framework for performance analysis and performance measurement. Fuzzy increases the application of data envelopment analysis. Measuring the performance of companies with the help of data envelopment analysis can help investors in choosing a company. In this paper, the problem of selecting fuzzy portfolios in a multipurpose framework is examined. A comprehensive model for selecting multi-purpose portfolios in fuzzy environment is presented using a semi-variance model and a model for analyzing information development with cross-sectional returns. Data from 40 companies accepted in Tehran Stock Exchange and trapezoidal returns of 40 sheets of securities and the data required for inputs and output of data envelopment analysis were obtained from financial statements of companies from the beginning of 1396 to the end of 1396. 16 financial parameters were used. Sharp ratio, cross-sectional return model in Sharp ratio and multi-purpose firefighting algorithm for solving multi-purpose stock optimization model was used. Analysis was done with MATLAB software. The results showed that the proposed method in this research is more suitable for selection of fuzzy multipurpose portfolio than other methods and provides better results for performance analysis, efficiency and company selection for investment.

Nowadays the growth in the use of social networks among different classes of world community is increasingly undeniable. Social networks database include Rich and valuable resources whose release and analysis with the purpose of marketing, publicity, National Security, Health and etc. can benefit researchers of public and private institutions. But respect the privacy of the entities whose information is available to data miner analysis is essential as a legal protocol. In this Paper, through qualitative methodology Meta synthesis, all related dimensions, indicators and codes were identified and then the importance and priority of each of the factors was determined. Subsequently, the improved model of anonymity was presented by an optimizing firefly algorithm and fuzzy clustering. The result of simulation and assessment of the proposed model on the data of four social networks such as Facebook, YouTube, Twitter and Google+ depicts that privacy preserving of data with the lowest distortion ratio and the more usefulness of data.

The purpose of this study is to investigate the application of Meta Heuristic Algorithms in Financial field. The studied algorithms in this study include ant colony algorithm, firefly algorithm, bee algorithm, harmony search, biogeography algorithm. while examining each of these algorithms in brief, internal and external studies are performed and their applications in the financial field are discussed. The results show that further research and ultimately the use of these algorithms in predicting financial and capital market issues can help to increase the performance of accounting and auditing operations to a researchable extent. Increasing research and providing operational backgrounds in recent years also reflect the interest of researchers and research organizations in developing these new approaches, especially in the field of software development.

Money demand is one of the most important economic variables which is a critical component in appointing and choosing an appropriate monetary policy because it determines the transmission of policy-driven change in monetary aggregates to real sector. Demand for M1 is simulated in this inquiry using FA and COA algorithms and three functional forms (linear, quadratic and exponential) are considered. Investigating the forecasting accuracy criteria indicated that the most subtle model is used for forecasting money demand up to 1404 horizon under three (optimistic, pessimistic and the middle) scenarios. More minuteness of COA, choosing exponential form as the most subtle functional form, the direct relation of GDP and the exchange rate with money demand, the reverse relation of inflation rate with money demand, 11.23 and 6.29 and 0.68 percent average growth rate of money under optimistic, pessimistic and the middle scenarios, and money demand decrease in pessimistic scenario form 1401, are some of the main results. The results of scenario designing and executing show that the efficiency and consequences of monetary authorities in accompany with money demand are dependent on appropriate policies about inflation and exchange rate.

On one hand, countries dependent on oil revenue have reached the conclusion that oil cannot be a reliable source of income and the oil dependent economy has become a major challenge for oil-exporting countries. On the other hand, in recent years tourism has become one of the most dynamic sectors of global economy and income from different capacities of the tourism industry is sought to replace the income from oil sales. Medical tourism is one of the important areas of the tourism industry. In this study, the effect of institutional indicators on medical tourism in Iran have been investigated using an optimization approach. The results of the study indicate that, Improvement in institutional quality index, gross fixed capital investment in public and private hospitals, gross fixed capital in tourism services, as well as an increase in the number of service providers to medical tourists, including general practitioners and specialists, and an increase in real effective exchange rates in Iran has led to an increase in the attraction of medical tourists to the country.

Predicting the future stock price has always been considered as an important issue by both buyers and sellers. Hence, Artificial Neural Network (ANN) was used in this study to develop a model pertaining to artificial intelligence in order to predict stock price in Iran Stock Market. Since artificial neural networks should consist of the best network topology to achieve the highest performance, Firefly Algorithm (FA), a meta-heuristic Algorithm, was used to find the optimal structure of network. Finally, Bayesian regulation technique, rather than the conventional teaching techniques, was applied to maintain the more generalized network. In general, Data from three big companies: Iran Khodro Company, Shiraz Petrochemical Company, and Isfahan Steel Companywere gathered in span of three years. This paper profited from some parameters, including high price, low price, the opening price, closing price, EMA (5) ،EMA (10) ،RSI ،William R% ،Stochastic k% ،Stochastic D% و ،ROCas network inputs and benefited from the closing stock price in the next days as the neural network as well. After developing a model associated with each company, some parameters such as the root-mean-square error (RMSE), Standard Deviation of error (SD), Absolute average relative deviation (AARD), the regression coefficient (R2) as well as the graphical analysis of relative deviation have been used to examine the accuracy of the developed network. The outcomes of the analysis of the developed neural networks revealed that the mentioned models with great accuracy are able to predict stock price in the subsequent day for the corporations mentioned above.