The Research Department of Economics and Management of Tadbir Nikan Business, Marketing, and Finance Open 3 Serial Number 13 2026 02 10 The Examination of the Probability of Negative Stock Returns Using Artificial Intelligence Optimization Algorithms The Examination of the Probability of Negative Stock Returns Using Artificial Intelligence Optimization Algorithms 1 13 10.61838/bmfopen.266 EN Journal Article 2025 03 21 <p>Accurately predicting the probability of negative stock returns is one of the central challenges in the field of finance and risk management, which, due to the complex, nonlinear, and non-stationary nature of capital market data, requires the use of advanced and modern analytical methods. Artificial intelligence optimization algorithms, especially metaheuristic algorithms such as Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), Harmony Search (HS), Firefly Algorithm (FA), and Biogeography-Based Optimization (BBO), with their ability to effectively search large and multidimensional parameter spaces and adaptive learning capabilities, are promising options for modeling and predicting negative stock returns. This study comprehensively examines the performance of these algorithms based on important financial risk criteria such as negative return skewness, maximum sigma, and low-to-high volatility, through statistical analysis of prediction errors (MSE and MAE). The obtained results indicate the statistically significant superiority of the Ant Colony Optimization algorithm in more accurately predicting negative returns compared to other algorithms and traditional models. The findings show that artificial intelligence optimization algorithms, utilizing natural and biological mechanisms, have the capability to model the complexities of the financial market.</p> https://www.bmfopen.com/index.php/bmfopen/article/download/266/286