درخت حوزه‌های تخصصی

Technical and fundamental analysis are the two principal methods for studying financial markets. However, access to internet and social media helps investors make better decisions. Social media has turned into a source of information for investors. Surowiecki (2005) found social media can predict better than individuals, known as the Wisdom of the Crowd. In this study, we tried to evaluate the wisdom of the crowd’s potential to improve stock price prediction accuracy. So, we developed a prediction model by Long Short-Term Memory based on the wisdom of the crowd. Persian users' opinions on Tehran Stock Exchange stocks were gathered for 8 months and classified as buying, sell, or neutral. During the research period, people mentioned 823 stocks and 52 stocks, which had over 100 recommendations, were chosen. Prediction model accuracy was increased for 19 stocks. While, for 33 stocks were not more accurate with the wisdom of the crowds and social media features. It is important to note that investors apply critical thinking. The wisdom of the crowd can be one input to the decision-making process, along with other related factors. The wisdom of the crowd provides an opportunity to access vast and diverse information. Getting opinions from various people can provide valuable insights into economics and investment preferences. The wisdom of the crowd can help reveal the flow of money. The combination of the wisdom of the crowd, fundamental, and technical analysis can be a useful tool for traders in detecting capital flow and profitable opportunities.

This study aims to develop a working capital management model for companies listed on the Tehran Stock Exchange. The proposed model determines the expected level of working capital for a company, enabling it to create the highest possible value. Additionally, this model can be used to assess the efficiency of working capital management. The discrepancy between the actual level of working capital and the expected level serves as an indicator of inefficiency in working capital management. Initially, based on theoretical foundations and expert opinions, 28 variables affecting working capital were selected. Then, using the operational working capital index, the research models were estimated using multiple regression and genetic algorithm techniques for data from 156 companies over the period from 2011 to 2022. Influential variables were identified and filtered. Finally, suitable working capital management models were identified based on two criteria: (1) the strong correlation between the errors of the fitted models and the working capital efficiency of the company, and (2) the model’s accuracy in identifying companies prone to excess or shortage of working capital. In total, after estimating 119 different models using regression and genetic algorithm methods, four suitable working capital management models were determined. The regression method resulted in models with an average accuracy of 77.27% and 79.54% for the dependent variable of working capital and the cash conversion cycle, respectively. The genetic algorithm method resulted in models with an average accuracy of 89.03% and 82.08%. The final model, with the cash conversion cycle as the dependent variable, was identified as the best model. It includes the variables of the previous year's cash conversion cycle, company-specific risk, gross profit margin, trade credit, growth opportunities, operating cycle, economic policy uncertainty, and exchange rate changes.