Today, the significant and rapid development of technology, along with extensive environmental changes, has given an accelerating pace to the field of economics; also, the increasing competition among institutions has limited profit margins and increased the likelihood of bankruptcy. Therefore, key stakeholders, managers, investors, and other commercial partners are interested in evaluating the financial position of a company and its tendency towards bankruptcy. Additionally, the financial distress of large international companies has made the issue of financial distress or, in other words, bankruptcy, a very important concept in the field of economics and financial sciences. This is because, in the event of bankruptcy, high costs are imposed on companies and the government; on the other hand, the bankruptcy of companies affects market liquidity and economic development. Furthermore, financial distress and bankruptcy of companies lead to the waste of resources and failure to take advantage of investment opportunities. During bankruptcy, banks usually reduce lending to bankrupt companies and demand higher interest rates for the loans they provide to compensate for the additional risk. Similarly, investment institutions such as pension funds and insurance companies reduce stock purchases and tend more towards investing in bank loans or similar markets. All of these factors lead to a decrease in liquidity in capital markets, increased costs for companies, and a decrease in economic growth.

The bankruptcy of large companies and the financial scandals of some companies in recent years justify the increasing need for more extensive and in-depth research in the field of financial distress. Financial distress is a situation where a company does not have enough cash flow to meet its financial obligations. In the literature on asset pricing, the concept of financial distress has been discussed to explain abnormal patterns in stock returns. Since changes in a company's capital are considered a future indicator of company risk, investors pay great attention to this when making decisions about investing in securities [1]. Therefore, analyzing a company that is experiencing financial distress is essential. On the other hand, having sufficient knowledge in the field of risk management and understanding the difference between systematic and unsystematic sources of financial distress is important for choosing active and passive investment strategies in securities of distressed companies. Additionally, studying the risky behavior of financial distress and its impact on the stock returns of companies is useful for understanding the incompatible processes in distressed companies before bankruptcy. It can be used to improve crisis management in companies. This research can be of great interest to banks and financial institutions, as when a company applies for a loan, these institutions must assess the possibility of bankruptcy before responding to loan requests, as they will bear the highest costs in the event of bankruptcy. Financial scandals have led to a decrease of hundreds of billions of dollars in market value and loss of investor confidence in capital markets. Therefore, investors and creditors have a strong inclination to predict the financial distress of companies. On the other hand, this prediction can serve as a warning for shareholders and company managers, as it can influence their decision-making. From a management perspective, the tool of predicting the bankruptcy of companies provides the opportunity to take timely strategic actions to prevent the waste of resources and take advantage of suitable investment opportunities.

The main goal of the present research is to understand better the factors affecting the bankruptcy of companies and to investigate and predict the bankruptcy point of companies based on their financial statements. Also, implementing these factors in artificial neural networks for more accurate prediction [2]. This research is applied in terms of goal, descriptive in terms of method, correlational in terms of research method, and modeling in terms of statistics [3]. In the present research, after library studies, variables for prediction were considered based on the best ratios in the results of previous research, such as the ratio of pre-interest and tax profit to total assets, current ratio (Current assets to current liabilities), the ratio of accumulated profit and loss to total assets, the ratio of shareholders' equity to total liabilities, and the ratio of total liabilities to total assets. The required data for this research was obtained by referring to the software archive of the Tehran Stock Exchange, the website of the Research and Islamic Studies Management of the Stock Exchange, and the Codal website and downloading all the financial statements of the companies listed on the stock exchange [4]. The population studied in this research consists of textile manufacturing companies listed on the stock exchange between the years 2011 and 2018. The sample used consisted of 21 textile companies whose information was available and were selected as follows:

First, a list of companies that had been subject to article 141 of the commercial law based on the company's legal inspector's report between the years 2011 and 2018 was prepared. Among them, 21 companies with available financial information were selected [5]. Then, based on the financial ratios that were selected using the backgrounds and the expert opinion matrix to find the weight of each, the Analytic Hierarchy Process (AHP) technique was used. After the options and indicators were determined, pairwise comparisons were made between the indicators. In this research, a questionnaire was prepared at this stage to measure pairwise comparisons between the criteria, and experts and accounting professors were used for this purpose. They were asked to rate the questionnaire with a numerical selection between one and nine based on the importance of the criteria.

Financial distress is a condition in which a company or individual cannot generate sufficient income, leading to the inability to fulfill or pay their financial obligations. Financial distress in a company often does not occur; however, when it does, the company's stock market value drops. Therefore, an early warning of imminent bankruptcy is necessary for accurate and prompt prediction to deal with the company's bankruptcy [12]. The main goal of the present research is to understand better the factors affecting financial distress in some stock companies and to examine and predict the point of financial distress in companies based on their financial statements. This research was conducted using the AHP-TOPSIS method and artificial neural networks [13]. Therefore, in the present study, in the first stage, the identification of factors causing financial distress in steel industry companies was carried out, followed by the selection of stock indicators, and then the ranking of indicators was done using a combination of AHP/TOPSIS methods.

Bankruptcy of companies can create major crises for shareholders, managers, and the country's economy, causing them to incur significant losses [14]. Therefore, researching to examine the financial bankruptcy of companies, identify its causes and factors, and be able to address company issues with problem-solving methods to prevent the loss of national wealth in the form of physical and human capital and its consequences becomes increasingly important. One of the important issues in the field of financial decision-making for any company is predicting its financial bankruptcy. From a management perspective, the tool for predicting financial bankruptcy provides the possibility to take timely strategic actions and avoid bankruptcy. Therefore, finding a model to predict the bankruptcy of companies is essential. The results obtained in this research show that, based on the prioritization that was done, among the five important selected factors, the current ratio has a higher priority compared to other factors, and by entering variables into an artificial neural network, the predictability capability can be increased [15]. The accuracy and precision of prediction can be improved to prevent financial crises and irreparable losses in unfavorable conditions with appropriate decisions.

Mohammad Eskandari Nasab Siahkoohi developed a systematic methodology for evaluating and ranking these factors to assist organizations, investors, and policymakers in reducing bankruptcy risks.

This research did not receive support from any particular grant offered by public, commercial, or non-profit funding organizations.

The data used in this study to evaluate the sustainability of suppliers are proprietary and cannot be disclosed to the public. Nevertheless, summarized information and methodological details may be provided upon reasonable request to the corresponding author.