Comparing the Power of Predicting Financial Helplessness in the Deep Learning Method Based on the Gray Wolf Optimization Algorithm with the Artificial Neural Network Method

Financial institutions model potential counterparty distress before lending to potential counterparties in an attempt to mitigate such losses. Therefore, one of the ways to help in the correct use of investment opportunities and also to prevent the wastage of resources is to predict financial helplessness. In this regard, in this research, a new model related to the prediction of financial helplessness is presented, in which the deep learning method based on the gray wolf optimization algorithm will be used. Then the predictive power of this model is compared with the artificial neural network method. For this purpose, the information of 160 selected firms admitted to the Tehran Stock Exchange during the period of 2016 to 2022 was used. The findings of the research related to predicting the helplessness of firms based on the deep learning method based on the gray wolf meta-engineering algorithm, showed that the percentage of success of this model in predicting the helplessness of companies is equal to 98.33%, while the power of prediction the artificial neural network method was for 94.45%. Based on this, it can be concluded that the deep learning method based on the gray wolf meta-engineering algorithm has a higher level of accuracy than the artificial neural network method in predicting the helplessness of the investigated firms