GC-TuneHFT: AI-Based Garbage Collection Optimization in High-Frequency Trading Environments
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V5I6P103Keywords:
High-Frequency Trading (Hft), Garbage Collection (Gc), Low Latency Systems, Jvm Optimization, Machine Learning, Reinforcement Learning, Real-Time Systems, Memory ManagementAbstract
High-frequency trading (HFT) practices call for extremely low latency, as even a tiny delay of just a few microseconds can influence the outcome of a transaction. As a direct consequence, garbage collection (GC) has become the main culprit behind the worsened performance of Java Virtual Machine (JVM)-based systems. GC-TuneHFT is a machine learning-based method which adjusts the GC environment dynamically to the workload locally. In order to relieve or even eliminate GC pauses it will, based on the system's predictions of memory usage, allocation spikes, and stop-the-world threats, automatically vary quite a few parameters such as the young generation size, the concurrent cycle triggers, and the promotion thresholds. GC-TuneHFT can shorten the waiting time, raise the throughput, reduce the tail latency (p99/p99.9) as well as improve the overall system stability under peak load-the condition which occurs frequently during times of market volatility. Among the future upgrades are the use of reinforcement learning for fully autonomous heuristic exploration, deeper integrations with the Java Virtual Machine (JVM) internals for fine-grained memory instrumentation, and the development of ever-evolving cloud-based auto-tuning pipelines for garbage collection (GC) that can handle a wide variety of high-frequency trading (HFT) workloads.
References
[1] Sadaf, R., McCullagh, O., Sheehan, B., Grey, C., King, E., & Cunneen, M. (2021). Algorithmic trading, high-frequency trading: implications for MiFID II and market abuse regulation (MAR) in the EU. High-frequency Trading: Implications for MiFID II and Market Abuse Regulation (MAR) in the EU (May 15, 2021).
[2] Akinade, A. O., Adepoju, P. A., Ige, A. B., Afolabi, A. I., & Amoo, O. O. (2022). Advancing segment routing technology: A new model for scalable and low-latency IP/MPLS backbone optimization. Open Access Research Journal of Science and Technology, 5(2), 77-95.
[3] Haider, S. A., Zikria, Y. B., Garg, S., Ahmad, S., Hassan, M. M., & AlQahtani, S. A. (2022). AI-based energy-efficient UAV-assisted IoT data collection with integrated trajectory and resource optimization. IEEE Wireless Communications, 29(6), 30-36.
[4] Strollo, E., Sansonetti, G., Mayer, M. C., Limongelli, C., & Micarelli, A. (2020, July). An AI-Based approach to automatic waste sorting. In International Conference on Human-Computer Interaction (pp. 662-669). Cham: Springer International Publishing.
[5] Parakala, Adityamallikarjunkumar. "Role Evolution: Developer, Analyst, Lead, Senior." American International Journal of Computer Science and Technology 4.3 (2022): 11-19.
[6] Abunama, T., Othman, F., Ansari, M., & El-Shafie, A. (2019). Leachate generation rate modeling using artificial intelligence algorithms aided by input optimization method for an MSW landfill. Environmental Science and Pollution Research, 26(4), 3368-3381.
[7] Chordia, T., Goyal, A., Lehmann, B. N., & Saar, G. (2013). High-frequency trading. Journal of Financial Markets, 16(4), 637-645.
[8] Guntupalli, Bhavitha. "The Role of Metadata in Modern ETL Architecture." International Journal of Artificial Intelligence, Data Science, and Machine Learning 2.3 (2021): 47-61.
[9] Boehmer, E., Li, D., & Saar, G. (2018). The competitive landscape of high-frequency trading firms. The Review of Financial Studies, 31(6), 2227-2276.
[10] Dragos, B., & Wilkins, I. (2014). An ecological/evolutionary perspective on high-frequency trading. Journal of Sustainable Finance & Investment, 4(2), 161-175.
[11] Serrano, A. S. (2020). High-frequency trading and systemic risk: A structured review of findings and policies. Review of Economics, 71(3), 169-195.
[12] Yang, S., Paddrik, M., Hayes, R., Todd, A., Kirilenko, A., Beling, P., & Scherer, W. (2012, March). Behavior based learning in identifying high frequency trading strategies. In 2012 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr) (pp. 1-8). IEEE.
[13] Parakala, Adityamallikarjunkumar, and Rangaram Pothula. "AI+ Document Understanding in UiPath: Solving Real Government Problems." International Journal of Artificial Intelligence, Data Science, and Machine Learning 3.3 (2022): 111-122.
[14] Guntupalli, Bhavitha. "Writing Maintainable Code in Fast-Moving Data Projects." International Journal of Emerging Trends in Computer Science and Information Technology 3.2 (2022): 65-74.
[15] Baldauf, M., & Mollner, J. (2020). High‐frequency trading and market performance. The Journal of Finance, 75(3), 1495-1526.
[16] McNamara, S. (2016). The law and ethics of high-frequency trading. Minn. JL Sci. & Tech., 17, 71.
[17] Guntupalli, Bhavitha. "Writing Maintainable Code in Fast-Moving Data Projects." International Journal of Emerging Trends in Computer Science and Information Technology 3.2 (2022): 65-74.
[18] Zook, M., & Grote, M. H. (2017). The microgeographies of global finance: High-frequency trading and the construction of information inequality. Environment and Planning A: Economy and Space, 49(1), 121-140.
[19] MacKenzie, D. (2014). A sociology of algorithms: High-frequency trading and the shaping of markets. Preprint. School of Social and Political Science, University of Edinburgh.
[20] O’hara, M. (2015). High frequency market microstructure. Journal of financial economics, 116(2), 257-270.
[21] Padala, S. (2022). Omnichannel AI-Enabled Healthcare Contact Centers: Enabling Seamless Patient Journey Continuity. International Journal of AI, BigData, Computational and Management Studies, 3(1), 133-139.
