The performance of AI-driven trading systems in various trade scenarios will be assessed in this study, focusing on historical performance analysis, statistical evaluation, and risk assessment. We assessed profitability, risk-adjusted returns, volatility, false positives, and false negatives through 10 trials of these systems. The historical performance analysis showed a mean trial profitability rate of 11.5%, indicating consistent financial gains. Risk-adjusted returns were averaging at 8.0%, indicating that given the right strategies and risk controls these have been effective. Despite fluctuations, volatility remains within a tolerable range: the average is 15.3%. The infrequency of false positives (mean: 2.3) and false negatives (mean: 1.4) demonstrates the accuracy and trustworthiness of AI-prompted trading signals. There are indications that these results suggest an AI-driven trading system holds promise for enhancing investment performance in dynamic market environments and managing risk as well. Employing advanced statistical techniques and looking at historical performance metrics will allow investors and traders to make informed choices, maximize portfolio returns, and hedge market risks. Nonetheless, the impact of FAI integration in stock trading is limited by data biases, model overfitting, and regulatory compliance ill. To enhance the capabilities of AI-driven trading systems for responsible and ethical use in financial markets, we need more research that focuses on addressing these challenges.