Journal of Management and Business Solutions 3092-7226 3 Serial Number 15 2025 10 16 Modeling Investors’ Financial Behavior During Capital Market Volatility and Forecasting Future Market Trends Using Genetic Algorithm Simulation Modeling Investors’ Financial Behavior During Capital Market Volatility and Forecasting Future Market Trends Using Genetic Algorithm Simulation 1 21 EN Journal Article 2025 06 25 <p class="Abstract" style="line-height: 150%;"><span lang="EN-GB" style="font-size: 8.0pt; line-height: 150%;">This study was conducted with the aim of modeling investors’ financial behavior during capital market volatility and forecasting future market trends using genetic algorithm simulation. The principal objective was to develop an integrated framework for the dynamic simulation of learning, selection, and evolution of investment strategies under conditions of uncertainty and to establish a bridge between behavioral finance and quantitative market forecasting. The present research adopted a mixed-methods approach (qualitative–quantitative). In the qualitative phase, through in-depth interviews with 20 experts and by applying grounded theory methodology and interpretive structural modeling, the factors and components of financial behavior were identified. In the quantitative phase, a researcher-developed questionnaire consisting of 30 items across four dimensions (risk tolerance, response to market volatility, buying and selling strategies, and liquidity and trading volume) was distributed among 350 active investors of the Tehran Stock Exchange. Financial behavior was ranked using the TOPSIS method, and the model was tested through structural equation modeling. Subsequently, future market trends were forecast using support vector machines and genetic algorithms implemented in Python software. The results indicated that large investors exhibited the most optimal financial behavior, with a closeness coefficient of 0.78. The model fit indices (GFI = 0.97, NFI = 0.93, RMSEA = 0.031) were satisfactory. The genetic algorithm achieved a coefficient of determination of 0.96, demonstrating very high accuracy in forecasting market trends. Scenario analysis revealed that improvements in liquidity and trading volume exerted the greatest impact on future market trends (21.55–23.69 percent), while risk tolerance constituted the second most influential factor (18.74–19.51 percent). Accordingly, genetic algorithms represent an efficient tool for modeling investors’ financial behavior and forecasting market trends. Enhancing the financial literacy of retail investors, particularly in the areas of liquidity management and rational risk tolerance, can contribute significantly to the stability of the capital market.</span></p> https://www.journalmbs.com/index.php/jmbs/article/download/135/98