درخت حوزه‌های تخصصی

One of the biggest risks in the economies of countries is the bankruptcy of industries and companies. Predicting the bankruptcy of companies and industries provides the opportunity for the government, investors, and shareholders to take strategic actions to deal withcrises and prevent potential losses. From an economic perspective, financial distress can be interpreted as the company being loss-making, in which case the company has failed to succeed. In fact, in this case, the company's rate of return is less than the cost of capital. Another form of financial distress occurs when the company fails to comply with one or more of the debt covenant terms, such as maintaining the current ratio or the special value ratio to total assets according to the contract. Therefore, there is no general agreement on the definition of financial distress, and the reasons that lead companies towards failure are very different. One possible reason for failure is the wrong direction ofthe company, which can be analyzed through the financial ratios of the companies. Since the 1960s, many studies have only examined financial ratios as indicators of failure. Therefore, the analysis is the basis for improving and developing failureprediction models. In this study, the influential variables in predicting bankruptcy were first selected using backgrounds. The most important factors were identified with the opinions of experts, and the weight of each criterion was obtained using the AHP technique. Then, these criteria were ranked using the TOPSIStechnique to identify the most important factors. After completing these steps, by entering these variables into an artificial neural network of the multilayer perceptron type as input and using the backpropagation algorithm to train the network, the prediction accuracy increased, and accurate and reliable results were obtained

Energy, besides other factors, production is considered the main factor in growth and economic development, and economics can play beneficial roles in the performance of different sectors. Hence, the country authorities should try to predict anything more precisely regarding energy consumption in the proper planning and guidance of consumption to control the way they desire energy demand and supply parameters. This paper aims to evaluate the hybrid model of artificial neural networks and genetic algorithms in forecasting demand energy to predict energy consumption in the country. A case study is energy consumption in Iran's transportation sector. So, for this review, we use the annual data on energy consumption of transport as a variable output of forecast models and data from the entire country's annual population, GDP, and the number of vehicles as the input variables. Evaluation results showed that themodel ofArtificial hybrid model of Neural Networks (ANN) and Genetic Algorithm (GA), campared toother models, has the highest accuracy in predicting energy demand in the transportation sector