modeling the co-movement of stocks between returns with negative and positive shocks of sentiment arising from the imbalance of orders using a tree-stage clustering approach

This study explores the impact of emotions on financial markets. recent re-search highlights the role of psychological factors in financial crises. inves-tors, not always rational, base asset risk decisions on emotions and beliefs. optimism, pessimism, and self-confidence influence decision-making pro-cesses over time. irrational investors can cause market prices to deviate from fundamental values. this emotional price anomaly can be seen as a persistent sentiment risk factor significantly affecting stock returns. the research inves-tigates the effect of emotional shocks (positive and negative) on order flow imbalances and their impact on price movements. a three-stage clustering approach is used. the sample includes 172 companies listed on the tehran stock exchange from 2021, with daily data extracted from rahvard navin software. information on independent and dependent variables is analysed using a three-step clustering method to identify different time scales. finally, regression analysis in matlab software is used to examine the relationship between variables within specified time intervals. the results reveal a positive relationship between positive shocks caused by order imbalances and compa-ny returns. this relationship is reversed for negative shocks. three-stage clustering separates companies based on co-movement, revealing distinct behaviour and relationships between variables within each cluster. these findings demonstrate the effectiveness of the three-step clustering method for analysing company data.