
Handbook of artificial intelligence and big data applications in investments
This handbook provides a comprehensive overview of artificial intelligence (AI) and big data applications in investments. It covers topics such as machine learning, natural language processing, trading algorithms, and AI-driven customer service. Aimed at finance professionals, it offers insights into practical use cases, challenges, and evolving trends in AI adoption, making it a valuable resource for those navigating the integration of these technologies in investment strategies.
Please login or join for free to read more.

OVERVIEW
Introduction
This handbook offers a detailed exploration of how artificial intelligence (AI) and big data are transforming the finance industry. It covers various topics, from machine learning and natural language processing to AI-driven customer service and symbolic AI. Each chapter, written by experts in their fields, provides insights into how these technologies are applied in investment management, offering finance professionals practical guidance on integrating AI and big data into their investment strategies to improve decision-making and performance.
Chapter 1: Machine learning and data science applications in investments
On machine learning applications in investments
Mike Chen and Weili Zhou outline the potential of machine learning (ML) in investment strategies. They discuss how ML algorithms excel in predicting equity returns and corporate earnings by identifying non-linear relationships in high-dimensional data. However, the report highlights the challenge posed by financial markets’ low signal-to-noise ratio. A recommendation for practitioners is to build expertise in using ML to enhance risk-adjusted returns.
Alternative data and AI in investment research
Ingrid Tierens and Dan Duggan explore how alternative data, combined with AI, offers new insights for investment research. They provide examples of how AI processes vast amounts of unstructured data, improving the accuracy of financial forecasts. The authors suggest that integrating alternative data sources into investment models can lead to better investment outcomes.
Data science for active and long-term fundamental investing
Kai Cui and Jonathan Shahrabani argue that data science can complement active, long-term investing strategies. By leveraging machine learning models, investors can better predict long-term financial trends. The authors recommend that firms adopt data-driven approaches to enhance their fundamental investment strategies.
Chapter 2: Natural language understanding, processing, and generation: investment applications
Unlocking insights and opportunities with NLP in asset management
Andrew Chin, Yuyu Fan, and Che Guan demonstrate how natural language processing (NLP) is used to analyse text data from financial reports, news, and earnings transcripts. NLP’s ability to gauge sentiment from large text data sets offers deeper insights into market sentiment, leading to more informed asset management strategies.
Advances in natural language understanding for investment management
Stefan Jansen details the evolution of NLP and natural language understanding (NLU) in investment management. He explains how advanced models like transformers have improved the interpretation of unstructured data, providing financial professionals with tools for better decision-making. He recommends investment firms incorporate these advanced models to stay competitive.
Extracting text-based ESG insights: a hands-on guide
Tal Sansani and Mikhail Samonov focus on applying NLP in ESG analysis, showcasing how AI can help investors extract meaningful insights from ESG-related documents. They argue that NLP provides a more efficient way to assess large volumes of ESG data and recommend its broader adoption for sustainable investment decision-making.
Chapter 3: Trading with machine learning and big data
Machine learning and big data trade execution support
Erin Stanton examines the role of machine learning in optimising trade execution. She discusses how ML models can identify patterns in trade data, improving execution strategies. The report highlights the potential for ML to reduce trading costs and suggests integrating ML-based execution models in trading operations.
Machine learning for microstructure data-driven execution algorithms
Peer Nagy, James Powrie, and Stefan Zohren delve into microstructure data and how ML can predict trading volumes, volatility, and spreads. Their research demonstrates that ML-based algorithms outperform traditional methods in predicting market movements. They recommend that trading firms adopt these techniques to optimise trading performance.
Chapter 4: Chatbot, knowledge graphs, and ai infrastructure
Intelligent customer service in finance
Xu Liang discusses the use of AI in financial customer service, particularly chatbots and knowledge graphs. These tools enable more efficient customer interactions by using AI to handle routine queries, reducing the need for human intervention. The recommendation is to integrate AI-based systems for more scalable and responsive customer service in finance.
Accelerated AI and use cases in investment management
Jochen Papenbrock of NVIDIA discusses the role of accelerated computing in investment management, showing how faster processing speeds improve the implementation of AI models. He provides several case studies, demonstrating how firms using accelerated AI saw significant improvements in predictive accuracy. The report suggests investment firms prioritise upgrading their AI infrastructure to enhance efficiency.
Symbolic AI: a case study
Huib Vaessen explores symbolic AI in a case study on real estate portfolio management. APG Asset Management utilised symbolic AI to automate decision-making in structured environments. While less flexible than machine learning, symbolic AI is effective in regulated sectors like real estate. The recommendation is for firms in structured asset classes to consider symbolic AI for improving decision-making efficiency.