ARTIFICIAL INTELLIGENCE-DRIVEN OPTIMIZATION OF HIGH-FREQUENCY TRADING STRATEGIES: ENHANCING PERFORMANCE AND MANAGING MARKET IMPACT

The rapid advancement of artificial intelligence (AI) has revolutionized high-frequency trading (HFT), offering unprecedented opportunities for strategy optimization and market impact management. This paper explores the transformative role of AI technologies—including machine learning, deep learning, and reinforcement learning—in refining HFT strategies to achieve superior returns and enhanced adaptability in dynamic financial markets. We begin by examining the foundational principles of HFT and its current applications, followed by an in-depth analysis of how AI-driven algorithms can improve trading efficiency, reduce latency, and mitigate risks. Additionally, the study investigates the impact of HFT on market microstructure, developing a comprehensive market impact model that incorporates liquidity dynamics and price volatility. Through empirical analysis, we evaluate the performance of various AI-enhanced trading strategies across diverse market conditions, highlighting their effectiveness as well as potential risks. This research not only advances the understanding of AI's role in HFT strategy optimization but also provides actionable insights for market participants to better navigate and manage the complexities of modern financial markets.