Article

The Impact of AI on Modern Trading: A Technical Overview

Authors:
To read the full-text of this research, you can request a copy directly from the author.

Abstract

This comprehensive article explores the transformative impact of Artificial Intelligence (AI) on financial trading, focusing on advanced machine learning algorithms, predictive analytics, and risk management strategies. It delves into the technical aspects of AI-powered trading systems, examining how they process real-time market data, execute high-frequency trades, and optimize trading strategies. The article discusses various machine learning models used for price prediction, including CNNs, RNNs, and SVMs, as well as sophisticated backtesting techniques. Additionally, it explores AI applications in risk management, covering sentiment analysis through NLP and volatility forecasting using enhanced GARCH models and extreme value theory. Throughout, the article highlights how these AI-driven approaches are revolutionizing market operations, improving efficiency, accuracy, and risk assessment in the financial sector.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Financial time series forecasting is undoubtedly the top choice of computational intelligence for finance researchers in both academia and the finance industry due to its broad implementation areas and substantial impact. Machine Learning (ML) researchers have created various models, and a vast number of studies have been published accordingly. As such, a significant number of surveys exist covering ML studies on financial time series forecasting. Lately, Deep Learning (DL) models have appeared within the field, with results that significantly outperform their traditional ML counterparts. Even though there is a growing interest in developing models for financial time series forecasting, there is a lack of review papers that solely focus on DL for finance. Hence, the motivation of this paper is to provide a comprehensive literature review of DL studies on financial time series forecasting implementation. We not only categorized the studies according to their intended forecasting implementation areas, such as index, forex, and commodity forecasting, but we also grouped them based on their DL model choices, such as Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), and Long-Short Term Memory (LSTM). We also tried to envision the future of the field by highlighting its possible setbacks and opportunities for the benefit of interested researchers.
Article
Long short-term memory (LSTM) networks are a state-of-the-art technique for sequence learning. They are less commonly applied to financial time series predictions, yet inherently suitable for this domain. We deploy LSTM networks for predicting out-of-sample directional movements for the constituent stocks of the S&P 500 from 1992 until 2015. With daily returns of 0.46 percent and a Sharpe ratio of 5.8 prior to transaction costs, we find LSTM networks to outperform memory-free classification methods, i.e., a random forest (RAF), a deep neural net (DNN), and a logistic regression classifier (LOG). The outperformance relative to the general market is very clear from 1992 to 2009, but as of 2010, excess returns seem to have been arbitraged away with LSTM profitability fluctuating around zero after transaction costs. We further unveil sources of profitability, thereby shedding light into the black box of artificial neural networks. Specifically, we find one common pattern among the stocks selected for trading - they exhibit high volatility and a short-term reversal return profile. Leveraging these findings, we are able to formalize a rules-based short-term reversal strategy that yields 0.23 percent prior to transaction costs. Further regression analysis unveils low exposure of the LSTM returns to common sources of systematic risk - also compared to the three benchmark models.
Article
In recent years, machine learning research has gained momentum: New developments in the field of deep learning allow for multiple levels of abstraction and are starting to supersede well-known and powerful tree-based techniques mainly operating on the original feature space. All these methods can be applied to various fields, including finance. This article implements and analyses the effectiveness of deep neural networks (DNN), gradient-boosted-trees (GBT), random forests (RAF), and several ensembles of these methods in the context of statistical arbitrage. Each model is trained on lagged returns of all stocks in the S&P 500, after elimination of survivor bias. From 1992 to 2015, daily one-day-ahead trading signals are generated based on the probability forecast of a stock to outperform the general market. The highest k probabilities are converted into long and the lowest k probabilities into short positions, thus censoring the less certain middle part of the ranking. Empirical findings are promising. A simple, equal-weighted ensemble (ENS1) consisting of one deep neural network, one gradient-boosted tree, and one random forest produces out-of-sample returns exceeding 0.45 percent per day for prior to transaction costs. Irrespective of the fact that profits are declining in recent years, our findings pose a severe challenge to the semi-strong form of market efficiency.
Book
The Handbook of News Analytics in Finance is a landmark publication bringing together the latest models and applications of News Analytics for asset pricing, portfolio construction, trading and risk control. The content of the Hand Book is organised to provide a rapid yet comprehensive understanding of this topic. Chapter 1 sets out an overview of News Analytics (NA) with an explanation of the technology and applications. The rest of the chapters are presented in four parts. Part 1 contains an explanation of methods and models which are used to measure and quantify news sentiment. In Part 2 the relationship between news events and discovery of abnormal returns (the elusive alpha) is discussed in detail by the leading researchers and industry experts. The material in this part also covers potential application of NA to trading and fund management. Part 3 covers the use of quantified news for the purpose of monitoring, early diagnostics and risk control. Part 4 is entirely industry focused; it contains insights of experts from leading technology (content) vendors. It also contains a discussion of technologies and finally a compact directory of content vendor and financial analytics companies in the marketplace of NA. The book draws equally upon the expertise of academics and practitioners who have developed these models and is supported by two major content vendors - RavenPack and Thomson Reuters - leading providers of news analytics software and machine readable news. The book will appeal to decision makers in the banking, finance and insurance services industry. In particular: asset managers; quantitative fund managers; hedge fund managers; algorithmic traders; proprietary (program) trading desks; sell-side firms; brokerage houses; risk managers and research departments will benefit from the unique insights into this new and pertinent area of financial modelling.
Article
Can we train the computer to beat experienced traders for financial assert trading? In this paper, we try to address this challenge by introducing a recurrent deep neural network (NN) for real-time financial signal representation and trading. Our model is inspired by two biological-related learning concepts of deep learning (DL) and reinforcement learning (RL). In the framework, the DL part automatically senses the dynamic market condition for informative feature learning. Then, the RL module interacts with deep representations and makes trading decisions to accumulate the ultimate rewards in an unknown environment. The learning system is implemented in a complex NN that exhibits both the deep and recurrent structures. Hence, we propose a task-aware backpropagation through time method to cope with the gradient vanishing issue in deep training. The robustness of the neural system is verified on both the stock and the commodity future markets under broad testing conditions.
Stock Trading Bot Using Deep Reinforcement Learning
  • A Azhikodan
  • A G K Bhat
  • M V Jadhav
A. Azhikodan, A. G. K. Bhat, and M. V. Jadhav, "Stock Trading Bot Using Deep Reinforcement Learning," in Innovations in Computer Science and Engineering, Singapore, 2019, pp. 41-49. [Online]. Available: https://link.springer.com/chapter/10.1007/978-981-13-7082-3_5
Big Data and AI Strategies
  • J P Morgan
J.P. Morgan, "Big Data and AI Strategies," J.P. Morgan Quantitative and Derivatives Strategy, May 2017. [Online]. Available: https://www.jpmorgan.com/global/research/machin e-learning
A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem
  • Z Jiang
  • D Xu
  • J Liang
Z. Jiang, D. Xu, and J. Liang, "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem," arXiv:1706.10059 [q-fin], Jun. 2017. [Online]. Available: https://arxiv.org/abs/1706.10059
Deep learning for event-driven stock prediction
  • X Ding
  • Y Zhang
  • T Liu
  • J Duan
X. Ding, Y. Zhang, T. Liu, and J. Duan, "Deep learning for event-driven stock prediction," in Proceedings of the 24th International Conference on Artificial Intelligence (IJCAI'15), Buenos Aires, Argentina, Jul. 2015, pp. 2327-2333. [Online]. Available: https://dl.acm.org/doi/10.5555/2832415.2832572
Financial Sentiment Analysis Using Pre-trained Language Models
  • F Yang
  • A Mukherjee
  • E Dragut
F. Yang, A. Mukherjee, and E. Dragut, "Financial Sentiment Analysis Using Pre-trained Language Models," in Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Spain, Dec. 2020, pp. 2259-2262. [Online]. Available: https://aclanthology.org/2020.coling-main.205