In the complex and dynamic stock market landscape, investors seek to optimize returns while minimizing risks associated with price volatility. Various innovative approaches have been proposed to achieve high profits by considering historical trends and social factors. Despite advancements, accurately predicting market dynamics remains a persistent challenge. This study introduces a novel deep reinforcement learning (DRL) architecture to forecast stock market returns effectively. Unlike traditional approaches requiring manual feature engineering, the proposed model leverages convolutional neural networks (CNNs) to directly process daily stock prices and financial indicators. The model addresses overfitting and data scarcity issues during training by replacing conventional Q-tables with convolutional layers. The optimization process minimizes the sum of squared errors, enhancing prediction accuracy. Experimental evaluations demonstrate the model's robustness, achieving a 67% improvement in directional accuracy over the buy-and-hold strategy across short-term and long-term horizons. These findings underscore the model’s adaptability and effectiveness in navigating complex market environments, offering a significant advancement in financial forecasting.

In recent years, fintech has received much attention due to the introduction of new technologies in banking and electronic payment. For financial service providers to compete in the industries, they should apply the business model as a conceptual framework to improve performance. The current research is exploratory and tries to identify the factors influencing fintech design in electronic payment using the Osterwalder business model. This study aims to integrate three methods named DEMATEL, ISM, and ANP from MCDM techniques. To analyze the identified factors affecting the design of fintech in electronic payment, the indicators were examined in terms of influence and effectiveness by the DEMATEL method, then the levels of influence and effectiveness of the factors were investigated using the interpretive structural modeling method. Finally, the network analysis method was used to prioritize the factors. The findings showed that recognizing and identifying electronic payment customers is the most effective among the factors, and determining the type of relationship with customers is the most impressionable factor. In addition, after ranking the factors, the type of relationship with customers was the first rank, and the criteria of the company's cost structure and revenue streams were determined as the second and third, respectively.

This research investigates the relationships between investors’ behavioral biases and compares their relative importance. For this purpose, a survey is conducted, and analytical methods are used. The sample for this study has been 512 individual investors of the Tehran Stock Exchange who completed an online questionnaire. The respondents replied about their behavior in different situations to analyze the prevalence of asymmetric discounting, mental accounting, shifting risk preference, loss aversion, regret aversion, overconfidence, proxy decision making, ambiguity aversion bias, anchoring, and herd behavior as significant fields of behavioral biases in their investment decisions. The data is analyzed using two different analytical techniques. A model based on structural equations is designed and tested to analyze the relations between these fields. Another integrated method, the DEMATEL-based analytic network process, is also used to prioritize and rank these behavioral biases. Finally, the results are compared and confirmed by each other. Analyzing the results proves the existence of 19 positive and statistically significant relations between these fields. Thus, an increase or decrease in the intensity of a particular field of behavioral biases in one’s decisions significantly affects the intensity of other fields. The present study finds that shifting risk preference, anchoring, loss aversion, and regret aversion are the most important fields of behavioral biases based on their prevalence among investors and their correlations with other biases.