جستجوی مقالات مرتبط با کلیدواژه « hybrid model » در نشریات گروه « مالی »

This study was aimed to predict financial distress using financial, economic and stock market variables in the form of binary logistic regression models, Merton and hybrid models. For this purpose, the information of 168 distressed companies selected based on specific criteria of distress and 168 healthy companies listed on the Tehran Stock Exchange between2006-2019 and two years ago, one year ago and distress year has been used. In this study, from 17 financial ratios, 4 economic variables and 4 stock market variables have been used. The innovation of the present study is the development of a hybrid financial distress prediction model that for the first time combines the financial, economic and stock market variables of the accounting model with the default variable of the structural model.The results showed that the hybrid model has better explanatory power than Merton and binary logistic regression model and although the existence of the variable probability of Merton model improves the explanatory power of the hybrid model, but the explanatory power of binary logistic regression model is better than the Merton model

The purpose of this study was to design a new model for predicting the Tehran Stock Exchange index using pattern recognition in a combination of hidden Markov model and artificial intelligence. The present study is an applied type and mathematical analytical method. Its location is the Tehran Stock Exchange and during the years 2010 to 2020. Findings showed that the prediction error rate with artificial neural network has a higher accuracy than Markov's hidden model. Also, the prediction error of the hybrid model is much lower than the other two models for predicting the total stock index of Tehran Stock Exchange, so it has higher accuracy for forecasting stocks. According to the MAPE index, the hybrid model method could improve the predictive power of the artificial neural network by 0.044% and also improve the predictive power of the hidden Markov model by 0.70%.

Financial distress, which is defined as the uncertainty about the company's ability to meet its obligations and repay its debts, has been estimated by different models divided into three groups of fundamental models (based on accounting or financial data), structural models (based on the company's capital structure or market information) and hybrid models.  Accurately predicting financial distress is still a major point of challenge for financial researchers. Scholars acknowledge that financial distress will be experienced when it happens. Therefore, the best thing to do is to initially estimate the probability of a company's financial distress. In this regard, in the current study, first, a hybrid model was presented to investigate the ability of financial distress prediction models. Next, in order to compare the hybrid model with accounting-based models, the second version of Altman's Z model known as the Z˝ model was used. To compare the hybrid model with market-based models, Merton's model was used in three groups including healthy, distressing, and distressed companies.

In this research, by reviewing past studies, 47 variables affecting financial distress, such as accounting variables, market variables, and macroeconomic indicators were identified. Afterward, considering the frequency and successful performance of these variables in past studies, 19 variables were selected. In the next step, using the Stepwise regression test, among the 19 variables, 10 variables with probability values ​​smaller than 0.05 were chosen. Also, to determine the dependent variable, the European option pricing model (Merton's model) was used. Finally, by the use of the Multinomial logit model and identifying the relationship between the dependent and independent variables, the hybrid model for predicting financial distress was designed. In order to compare the produced hybrid model with accounting-based fundamental models, the second version of Altman's Z model known as the Z˝ model was used. To compare the hybrid model with market-based structural models, Merton's model was used. Moreover, in order to test the ability of financial distress prediction models, a sample including 100 companies listed on the Tehran Stock Exchange (TSE) or Iran FaraBourse (IFB) was selected. Then, considering the defined criteria, these companies were divided into three groups consisting of healthy, distressing, and distressed companies. Finally, the ability of the above-mentioned models in predicting financial distress was investigated.

Research findings indicated that in the hybrid model, the ratios of Net Working Capital to Total Assets (WCTA), Operating Cash Flow to Total Assets (OCTA), Sales to Total Assets (STA), Net Income to Total Assets (NITA), Short-term and Long-term Debts to Equity (TLTE), Price to Earnings Per Share (P/E) and Price to Sales (P/S), and the variable of Interest Rate (INT) had significant relations with company's financial distress probability. Also, a comparison of the hybrid model and conventional models revealed that in the group of financially distressed companies, respectively, the Z˝ model with 100% accuracy, Merton's model with 85% accuracy, and the hybrid model with 90% accuracy had correctly predicted the financial situation of the companies. While, in the group of financially distressing companies, the accuracy of the Z˝ model, Merton's model, and the hybrid model in predicting the financial situation of the companies, stood at 50%, 85%, and 85%, respectively. In addition, in the group of healthy companies, these models were able to correctly predict 95%, 85%, and 90% of the companies' financial situation, respectively.

According to achieved results, the Z˝ model has higher predictive power on healthy and distressed companies, compared to the hybrid and Merton models. While, the hybrid and Merton models are better at predicting the financial situation of distressing companies than the Z˝ model. Therefore, considering that the performance of the market-based model of Merton in predicting the financial situation of the companies is weaker than those of the Z˝ and that the hybrid models which are mainly formed by financial or accounting ratios, and also in regard to the findings of past studies which proved the inefficiency of the stock market in Iran, it can be concluded that it is better to use accounting variables in future research in the field of predicting financial distress.

Corporate financial distress is the most unpleasant event that will result in catastrophic issues for its stakeholders. In addition to the huge losses for the business itself, this event can potentially affect the country's economy. Therefore, quick and timely detection of financial distress is essential to support various financial and social investments. In this regard, the present study aimed at providing a combined model of corporate default prediction and classifying firms into three groups: healthy, stressed and distressed. In this study, first, using a library research method, 47 variables or ratios were identified, selected and classified into three groups: fundamental or financial variables, market variables and macroeconomic variables. Then, considering the frequency and successful performance of these ratios in previous studies and by performing statistical tests, potential variables affecting financial distress were identified. In this study, multinomial logistic regression was used to provide a combined model of corporate default prediction. Also, in order to measure corporate default, the Black-Scholes-Merton (BSM) model was used. Findings indicated that 8 variables, including 5 financial variables, 2 market variables and 1 macroeconomic variable were statistically significant in the final model, and in fiscal year 1398, the accuracy of this model was 90% in the group of distressed firms, 85% in the group of stressed firms and 90% in the group of healthy firms.

This study presents the new hybrid network of GARCH family and an artificial neural network to predict the Tehran Stock Exchange index during the period of 2008-2017. The existence of long-term memory in the conditional variance of the Tehran stock returns causes use in addition GARCH and EGARCH models with short- memory, long-term memory models. In addition to long-term memory models, considering the better performance of hybrid models in predicting financial data of the Garch family models (short and long-term) are combined with the artificial neural network. Using hybrid models the return of stock index was forecast for the next 10 days and its accuracy was evaluated using the evaluation criteria. The results showed that the hybrid FIEGARCH with the student-t distribution model was more efficient in forecasting return of stock and had a lower forecast error than others models

Capital asset pricing model (CAPM) has been among the most common models to estimate the expected return. In the standard CAPM model, a) the beta coefficient is fixed and b) the relationship between stock returns and market returns is assumed to be linear. While in financial markets, it is possible that the beta coefficient varies over time by changing the cost-benefit analysis on returns and risks, and also in a nonlinear environment, the beta coefficient estimate will be linearly inappropriate and oblique. Therefore, it seems necessary to use other models in estimating expected return. In this study, in addition to the standard CAPM model, the threshold regression and kernel regression models were used to estimate the CAPM model. Considering that the basis of each of these models is based on different assumptions; therefore, this research has tried to use a genetic algorithm in the time period from 2008 to 2017 to propose a hybrid model in order to estimate the expected return. Expected return was calculated using standard CAPM, threshold regression, kernel regression and the hybrid model of these three models, and the results were compared with the realized returns. The mean square error (MSE) index was used to measure the predictive power of research models. Using the paired t-test on the mean square error, the research models were compared with each other. The results show that applying the hybrid model increases the predictive power of realized return compared to other research models.

In general, financial time series such as stock indexes have nonlinear, mutable and noisy behavior. Structural and statistical models and machine learning-based models are often unable to accurately predict series with such a behavior. Accordingly, the aim of the present study is to present a new hybrid model using the advantages of the GMDH method and Non-dominated Sorting Genetic Algorithm II (NSGA II) to, more accurately, predict the trend of movement and volatility of Tehran Stock Exchange Price Index, and to compare its ability with the ARIMA model based on RMSE, MAPE, and TIC error assessment criterions. For this purpose, the data of Tehran Stock Exchange Dividend and Price Index (TEDPIX) was used during the period of October 2008 to September 2013. The hybrid model NSGA II - GMDH utilizes the GMDH network as a model resistant to nonstationary and noisy data for prediction and uses the NSGA II multi-objective optimization algorithm to minimize predictive error and select the optimal input variables. The results of the proposed hybrid model in this study indicated a lower error and more prediction accuracy compared to ARIMA model for out-of-sample data based on all three error criterions. The empirical findings of the study showed that the proposed model has higher flexibility and capability in covering unstable changes in the total index movement trend

Price forecasting is one of the most challenging issues that the speculators, traders and brokers are faced with. On the other hand in interval analysis it is supposed that observations and estimations in the real world are not complete and reliable so to increase the accuracy we should describe the data as the intervals that includes real quantities. Various methods are used in order to model the time series such as price. Autoregressive integration moving average (ARIMA), which is known as box-Jenkins method is one of the most commonly used models in forecasting of time series during the past three decades. But the main assumption is that there is a linear relationship between the values of the series therefore nonlinear relationships cannot be explained completely by using autoregressive integration moving average (ARIMA). Another method in time series forecasting is neural network which can estimate the various nonlinear relationship (called neural network universal estimating) but according to the literature, using network will have complicated results. Since it is difficult to understand the linear and nonlinear data pattern in reality, this idea will come to mind that the combination of linear and nonlinear models could increase the accuracy of forecasting. So in this research the linear part will be estimated by ARIMA and then the non-linear residuals will be modeled by neural network and finally the predicted result will be added to ARIMA in order to forecast the low, high and close price of gold .comparing the accuracy of the hybrid model to ARIMA and neural network by pair compared, Diebold-Mariano and Harvey-Newbold –Leybourn test and two criteria (MSE and MAE) showed that the hybrid model presented better performance.

Predicting the risk of financial bankruptcy is one of the most important issues in the field of companies’ financial decision. Accordingly, a variety of models that each is different in terms of predictor variables and techniques has been introduced so far. The use of the combination of accounting and market-driven variables in the model as input will have definitely a direct impact on the results and accuracy of forecasts. In this study, the prediction was accomplished by using a hybrid model (the use of accounting and market-driven variables) and neural networks technique of multi-layer perceptron model (MLP). The sample of research consists of 90 accepted companies in Tehran Stock Exchange (31 bankrupted companies in accordance with article Iran’s 141 trade laws and 59 non-bankrupted companies) during 2007-2014 period. The research results show that the hybrid model (combination of accounting and market-driven variables) using neural network technique has higher accuracy than each of the two accounting models and market-driven model in predicting the risk of financial bankruptcy. Likewise, the market-driven model is more accurate than accounting model.

Forecasting stock market price index has always been a challenging task, since it is affected by many economic and non-economic factors; therefore, selecting the best and the most efficient forecasting model is difficult.The time series in the real world, including the stock price index time series, rarely have a pure linear or non-linear structure. The Exponential Smoothing Model, Autoregressive Integrated Moving Average Model, and Nonlinear Autoregressive Neural Network can be used to make forecasts based on time series. In this research, to take advantage of all these models and to reduce forecasting errors, a novel approach was tested by the linear combination of the results of these models.Weights used to combine the results, were determined using Genetic Algorithm and also equal weights. After determining the predictability of time series (using variance ratio test) the proposed hybrid methods were used on a monthly set of Tehran Stock Exchange Price Index (TEPIX). The results showed an improvement in forecasts made by this method with using equal weights compared to each of its constituent models.

Fluctuations in crude oil prices in addition to affect the economy of the exporting countries, is one of the sources of disruption in oil-dependent economy. Always predict the price and volatility has been of the challenges facing traders in oil markets and price forecast is raised as an imperative and functional however, should be noted forecasts that will take place in more accurate and less error than the observed actual results. In order to predict the weekly price of Brent crude oil as an oil indicator given the difficulty of accurately identifying linear and nonlinear models in economic and financial time series from combining Autoregressive Integrated Moving Average models (ARIMA) by the assumption that the time series have a linear pattern and support vector machine (SVM) which has great potential in modeling nonlinear model is used to enhance the accuracy of prediction. Given two paired comparison performance criteria of root mean square error test (RMSE) and the mean absolute magnitude percentage error (MDAPE) which are resulting from the predicted values ​​and actual values ​​for each model, this indicates that in most cases the hybrid model provide smaller errors in predicting the future price of crude oil as compared to the individual applications of autoregressive integrated moving average models and the support vector machine.