AI AND ALGORITHMIC TRADING: A STUDY ON PREDICTIVE ACCURACY AND MARKET EFFICIENCY IN FINTECH APPLICATIONS

Vandana Srivastava; Rajiv Sikroria

doi:10.29121/shodhkosh.v5.i1.2024.2797

Authors

Dr. Vandana Srivastava Assistant Professor, Faculty of Commerce, Banaras Hindu University, Varanasi
Dr. Rajiv Sikroria Assistant Professor, Department of Management, Sunbeam Women’s College Varuna , Varanasi

DOI:

https://doi.org/10.29121/shodhkosh.v5.i1.2024.2797

Keywords:

Artificial intelligence (AI), Algorithmic Trading, Predictive Accuracy, Market Efficiency, Financial Technology (FinTech), Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), Price Prediction, Risk Assessment, Portfolio Management, Market Liquidity, Trade Execution, Data Biases, Overfitting, Ethical Implications, Regulatory Oversight, Market Volatility, Trading Efficiency

Abstract [English]

The advent of artificial intelligence (AI) and algorithmic trading has revolutionized the financial technology (FinTech) landscape, offering enhanced predictive models and improving market efficiency. This study explores the integration of AI into algorithmic trading systems, focusing on their ability to forecast market movements and optimize trade execution. By analyzing various AI-driven techniques, such as machine learning (ML), deep learning (DL), and natural language processing (NLP), the research evaluates their impact on predictive accuracy and market liquidity. The paper investigates the role of AI in improving trade decision-making processes, including price predictions, risk assessment, and portfolio management. It also examines how these innovations contribute to market efficiency by reducing human errors, latency, and transaction costs, and by promoting faster market reactions to new information. Case studies and empirical data are used to compare the performance of AI-enhanced algorithms with traditional models. Furthermore, the study addresses potential challenges such as the risks of overfitting, data biases, and the ethical implications of AI-driven trading. The findings suggest that while AI significantly boosts predictive accuracy and trading efficiency, it also raises concerns about market volatility, fairness, and regulatory oversight. This research highlights the transformative potential of AI in financial markets, urging a balanced approach to its adoption to ensure both profitability and stability.

References

Buehler, D., Mittermeier, L., & Kolb, R. (2018). A deep learning approach to stock market prediction. Journal of Financial Data Science, 5(3), 45-60.

Cappella, L., D'Antoni, G., & Muccio, P. (2019). The regulatory implications of AI in high-frequency trading and algorithmic market manipulation. Journal of Financial Markets, 22(2), 102-116.

Feng, H., Yang, Z., & Ma, L. (2021). Market efficiency and the role of AI in price discovery. Journal of Financial and Quantitative Analysis, 56(1), 63-85.

Hasan, M., Lakhani, P., & Singh, A. (2020). Exploring the impact of AI-based algorithms on financial market efficiency. Journal of FinTech Research, 19(4), 221-235.

Jiang, Z., Zhang, X., & Li, Y. (2017). Application of machine learning algorithms in stock price prediction: A survey. International Journal of Financial Engineering, 12(5), 213-230.

Li, H., Yang, Y., & Zhou, X. (2019). Traditional algorithms vs. AI-based models in quantitative trading. Journal of Algorithmic Finance, 6(1), 99-115.

Nguyen, M., & Arora, A. (2020). AI in algorithmic trading: Ethical implications and regulatory challenges. International Journal of FinTech, 14(3), 190-204.

Vovk, V., & Wang, L. (2018). Reinforcement learning algorithms in algorithmic trading: An overview. Quantitative Finance Letters, 10(2), 88-101.

Zhang, L., Zhang, Y., & Liu, J. (2020). Stock market prediction using machine learning algorithms: A survey. International Journal of Computational Finance, 23(2), 143-160.

Benhamouda, S., & Temimi, M. (2020). Exploring machine learning techniques in high-frequency trading for improved market prediction. Journal of Computational Finance, 24(4), 50-67.

Jin, Y., & Wang, X. (2019). Deep learning in financial markets: Survey and future directions. Journal of Financial Technologies, 28(3), 122-134.

Petrovic, D., & Klinc, R. (2018). A survey on predictive models for stock market price prediction. Journal of Finance and Data Science, 9(2), 34-49.

He, Z., & Li, J. (2021). Artificial intelligence applications in financial market prediction: Trends and challenges. Journal of Financial Modeling, 6(1), 78-95.

Yuen, C., & Cheung, H. (2020). A comparative study of traditional and machine learning models for stock price prediction. Journal of Quantitative Analysis, 32(3), 179-195.

Kumar, S., & Shukla, S. (2021). Analyzing the impact of AI in predictive finance and algorithmic trading. International Journal of AI and Financial Engineering, 17(5), 232-245.

Donadio, M., & Rossi, L. (2019). Challenges in implementing AI in algorithmic trading: A review of practical applications. International Review of Financial Economics, 26(1), 50-62.

Andrews, P., & Moore, R. (2019). Big data, AI, and their effect on financial market efficiency. Financial Review, 46(3), 167-180.

Ferguson, T., & Jain, R. (2020). Machine learning techniques and their role in improving stock market prediction accuracy. International Journal of Computational Economics, 34(2), 102-114.

Chowdhury, D., & Parsa, P. (2018). Stock prediction using AI-based algorithms: A systematic review. Journal of Applied AI, 8(4), 34-44.

Singh, M., & Agrawal, S. (2021). The evolution of predictive models in FinTech: From traditional algorithms to AI-based systems. International Journal of Financial Technologies, 30(2), 113-126.