摘要
本文旨在对人工智能平台在量化投资领域的应用进行深入的探讨与分析。首先,我们介绍了人工智能平台在量化投资领域的背景以及早期、近期和当前的发展阶段。然后在方法论上,我们以“Qlib”作为典型的人工智能平台案例,说明人工智能平台在量化投资策略开发中的应用影响。为此,我们首先详细梳理了该平台的框架,并对其模块化和流程管理的特点进行了鲜明的阐述,以便更好地理解人工智能平台在量化投资策略设计中的运作机制。然后,我们引入了一种性能评估方法,将Qlib与其他传统解决方案进行了比较。结果表明,人工智能平台的应用将有效缩短加载时间,通过利用多核CPU的效用使设计过程更加高效,同时由于模块化,开发过程更加灵活。最后,我们讨论了人工智能平台应用的局限性,并展望了未来的发展趋势。
关键词: 人工智能平台应用;Qlib;平台框架;性能评估
Abstract
The purpose of this article is to provide for an in-depth discussion and examination of the application of AI platform in quantitative investment field. First, we introduce the background of the AI platform in quantitative investment as well as its development stage in early, recent and current time. Then in terms of methodology we take “Qlib” as a typical AI platform case to illustrate the impact of the application of AI platform in the development of quantitative investment strategy. To do it first the framework of the platform was sort out in detail with distinctive characteristics of modularization and process management in order to better understand the operation mechanism of the AI platform in the design of quantitative investment strategy. Then a performance evaluation method is introduced to make the comparison between the Qlib with other traditional solutions. The outcome shows that the application of AI platform will effectively shorten the loading time and make the design process more efficient by leveraging the utility of multi-core CPUs as well as making the development process more flexible due to modularization. Finally, we discuss the limitation of the application of AI platform and look forward to the development trend in the future.
Key words: Application of AI platform; Qlib; Platform framework; Performance evaluation
参考文献 References
[1] Klaus Adam, Albert Marcet, and Juan Pablo Nicolini. Stock market volatility and learning, 2016.
[2] Franklin Allen and Risto Karjalainen. Using genetic algorithms to find technical trad¬ing rules. Journal of financial Economics, 51(2):245-271, 1999.
[3] John Bollinger. Bollinger on Bollinger bands. McGraw Hill Professional, 2002.
[4] Kristina Chodorow. MongoDB: the definitive guide: powerful and scalable data storage.'' O'Reilly Media, Inc.', 2013.
[5] Yue Deng, FengBao, Youyong Kong, ZhiquanRen, and Qionghai Dai.Deep direct reinforcement learning for financial signal representation and trading. IEEE transactions on neural networks and learning systems, 28(3):653-664, 2016.
[6] FuliFeng, Huimin Chen, Xiangnan He, Ji Ding, Maosong Sun, and Tat-Seng Chua. Enhancing stock movement prediction with adversarial training. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, pages 5843-5849. AAAI Press, 2019.
[7] V Kaul, S Enslin, SA Gross. History of artificial intelligence in medicine. Gastrointestinal endoscopy, 2020.
[8] A Bohr, K Memarzadeh. The rise of artificial intelligence in healthcare applications. Artificial Intelligence in healthcare, 2020.