hybrid algorithm

In today's financial landscape, the prediction of corporate financial distress plays a crucial role in risk management and economic stability. This study aims to develop a hybrid predictive model that combines the Artificial Immune System (AIS) with the Wavelet Neural Network (WNN) to forecast financial distress in companies. The hybrid model leverages the strengths of both algorithms to improve accuracy in identifying distressed firms based on financial data. Utilizing a dataset of Tehran Stock Exchange-listed companies, this research compares the performance of the hybrid model against traditional methods like logistic regression and standalone neural networks. Results demonstrate that the AIS-WNN hybrid model outperforms other techniques in terms of prediction accuracy, sensitivity, and overall robustness. The findings indicate that the proposed model provides a powerful tool for investors, auditors, and policymakers to anticipate financial distress and make informed decisions. This approach can be further expanded to other domains of financial forecasting, contributing to the advancement of predictive analytics in the field.

The purpose of this research is to investigate the impact of meta-heuristic hybrid algorithm analysis on portfolio diversification and excess returns of investment funds. In terms of method, the current research is a part of correlation research. In correlation research, the researcher's effort is focused on discovering or determining the relationship between one or more variables. In fact, the purpose of this method is to study the limits of changes of one or more variables with the limits of changes of one or more variables, and from the point of view of the purpose of this research, it is an applied research, the results of which can be useful for shareholders, stock exchange officials, and researchers. It is useful and in terms of the type of post-event studies that examines hypotheses based on past financial data. The statistical population of this research includes all the companies admitted to the Tehran Stock Exchange during the period of 36 months in the period from April 2019 to March 2011, which number is 591 companies based on the Rahevard software. According to the conditions and application of the aforementioned restrictions, 150 companies were selected as a sample in the 36 months ending in March 1401. By observing the results of the stock portfolio selection models with single and combined measures, we find that in all three models, the amount of risk increases with the increase in return. This shows that investors, in order to obtain more return, They are forced to accept

In the pharmaceutical supply chain, pharmaceutical products must be distributed among consumers with good quality at the right time and in the right place. Medicineis a product which affects the health of society and its timely delivery to consumers is of great importance. Therefore, it requires proper planning for its production and distribution. In this paper, we developed a model that minimize the cost of production, inventory, delivery, earliness and tardiness. We also assumed the uncertainty of demand and solved the linear mathematical model using stochastic programming and we solved the problem with stochastic programming. Also, due to the fact that the model with the objective function of earliness and tardiness with different delivery times of NP-hard problem for this problem, a hybrid genetic and variable neighborhood search algorithm were presented. Here, five scenarios were considered, the expected value of perfect information (EVPI) was measured and the obtained results were compared with the two-stage random-scheduling model. The computational results showed the efficiency of the developed model. Also, the results of the proposed hybrid algorithm were compared with the genetic algorithm, and the results showed that in terms of objective function, the hybrid algorithm has a much better performance compared to the genetic algorithm.