International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Driven Algorithmic Trading Framework for Financial Markets |
|---|---|
| ABSTRACT | The rapid evolution of financial markets, characterized by high-frequency trad-ing, extreme volatility, and enormous data volumes, has rendered traditional rule-based trading strategies largely inadequate. While algorithmic trading of-fers automation and speed, existing models frequently struggle to adapt to the non-stationary, stochastic nature of financial time-series data, resulting in sub-optimal portfolio returns and elevated risk exposure. To address these critical limitations, this paper presents a robust, end-to-end AI-driven algorithmic trad-ing framework capable of autonomous signal generation, portfolio optimization, and real-time order execution. The proposed system integrates a multi-modal deep learning architecture—specifically a Temporal Convolutional Network (TCN) combined with a Transformer-based attention mechanism—to simultaneously cap-ture short-range price momentum and long-range macroeconomic dependencies from heterogeneous data sources including OHLCV price feeds, technical indica-tors, and sentiment signals derived from financial news. A reinforcement learning agent, trained using the Proximal Policy Optimization (PPO) algorithm, governs dynamic position sizing and risk management decisions. The framework was eval-uated on historical equity data spanning five years across multiple asset classes. It achieved a Sharpe Ratio of 2.31, an annualized return of 28.7%, and a maximum drawdown of 9.4%, significantly outperforming both the buy-and-hold benchmark and state-of-the-art LSTM-based baselines. The results demonstrate that the pro-posed system is highly viable for live deployment, successfully bridging the gap between high-accuracy market prediction and the strict latency requirements of real-time trade execution. |
| AUTHOR | SWAPNIL SHINDE, PROF. DR. S. A. ITKAR, Y. P. NARWADKAR M.Tech Student, Department of Computer Engineering, P.E.S College of Engineering, Affiliated to SPPU, Pune, India Head of Department, Department of Computer Engineering, P.E.S College of Engineering, Affiliated to SPPU, Pune, India Guide, Department of Computer Engineering, P.E.S College of Engineering, Affiliated to SPPU, Pune, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406012 |
| pdf/12_AI-Driven Algorithmic Trading Framework for Financial Markets.pdf | |
| KEYWORDS | |
| References | [1] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention Is All You Need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 5998–6008. [2] S. Bai, J. Z. Kolter, and V. Koltun, “An Empirical Evaluation of Generic Con-volutional and Recurrent Networks for Sequence Modeling,” arXiv preprint arXiv:1803.01271, 2018. [3] J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal Policy Optimization Algorithms,” arXiv preprint arXiv:1707.06347, 2017. [4] Z. Jiang, D. Xu, and J. Liang, “A Deep Reinforcement Learning Frame-work for the Financial Portfolio Management Problem,” arXiv preprint arXiv:1706.10059, 2017. [5] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Com-putation, vol. 9, no. 8, pp. 1735–1780, 1997. [6] D. Araci, “FinBERT: Financial Sentiment Analysis with Pre-trained Lan-guage Models,” arXiv preprint arXiv:1908.10063, 2019. [7] H. Markowitz, “Portfolio Selection,” The Journal of Finance, vol. 7, no. 1, pp. 77–91, 1952. [8] M. Lo´pez de Prado, Advances in Financial Machine Learning. Hoboken, NJ, USA: Wiley, 2018. [9] B. Lim, S. O. Arik, N. Loeff, and T. Pfister, “Temporal Fusion Transform-ers for Interpretable Multi-horizon Time Series Forecasting,” International Journal of Forecasting, vol. 37, no. 4, pp. 1748–1764, 2021. [10] W. F. Sharpe, “The Sharpe Ratio,” The Journal of Portfolio Management, vol. 21, no. 1, pp. 49–58, 1994. [11] J. B. Heaton, N. G. Polson, and J. H. Witte, “Deep Learning for Finance: Deep Portfolios,” Applied Stochastic Models in Business and Industry, vol. 33, no. 1, pp. 3–12, 2017. [12] A. S. Kyle, “Continuous Auctions and Insider Trading,” Econometrica, vol. 53, no. 6, pp. 1315–1335, 1985. [13] R. Feng, D. He, J. Patouillard, H. Larochelle, and H. M. Nguyen, “Deep Transfer Learning for Financial Return Prediction,” in Proc. ACM Int. Conf. AI in Finance (ICAIF), 2021, pp. 1–9. [14] Y. Liu, Q. Liu, H. Zhao, Z. Pan, C. Liu, L. Wang, and J. Zhu, “Adap-tive Quantitative Trading: An Imitative Deep Reinforcement Learning Ap-proach,” in Proc. AAAI Conf. Artificial Intelligence, vol. 34, 2020, pp. 2128–2135. [15] P. Jorion, Value at Risk: The New Benchmark for Managing Financial Risk, 3rd ed. New York, NY, USA: McGraw-Hill, 2006. |
