The incorporation of artificial intelligence into an important change in how financial markets operate is represented by algorithmic trading. operate, evolving from traditional rule-based approaches to advanced machine learning methods that are capable of adapting to volatile market dynamics. The research examines the application of three key AI models – Random Forest regression, gradient boosting regression, and support vector regression predicting trading signal strength. The study uses a dataset containing twenty observations of six essential financial indicators frequently used in algorithmic trading: price momentum, volatility index, trading volume, moving average convergence divergence (MACD), and relative strength index (RSI) and trading signal strength. These indicators collectively provide a comprehensive view of market trends, price behavior, trading activity and signal reliability. The methodology involves a comparative evaluation of the three regression models, assessing their predictive accuracy through metrics such as R², explained variance score, The mean absolute error and the mean square error. The findings indicate that Support Vector Regression outperformed the other models with a test R² of 0.9478, followed by Slope Boosting Regression (0.8460) and Random Forest Regression (0.8388). The SVR showed strong consistency between training and testing results, indicating good generalization and minimal overfitting. Correlation analysis identified strong positive correlations between trading signal strength and several technical indicators, while the volatility index was negatively correlated with most variables. The findings emphasize the transformative impact of AI on market performance, liquidity, and risk management. However, challenges such as increased market volatility, systemic risks from high-frequency trading, cybersecurity threats, and the need for enhanced regulatory measures are also highlighted. The study concludes that while AI has significantly improved trading capabilities, its effective use requires significant investments in technology, skilled expertise, and management to uphold ethical standards and market stability.
A Thu, study studied this question.