Professional financial traders are currently overwhelmed with news and extracting relevant information is a long and hard task, whilst trading decisions require immediate actions. Primarily intended for financial organizations and business analysts, this book provides an introduction to the algorithmic solutions to automatically extract the desired information from Internet news and obtain it in a well structured form. It places emphasis on the principles of the method rather than its numerical implementation, omitting the mathematical details that might otherwise obscure the text, and focuses on the advantages and on the problems of each method. The authors also include many practical examples with complete references and algorithms for similar problems, which may be useful in the financial field, and basic techniques applied in other information extraction fields which may be imported into the financial news analysis.

This open access book covers the use of data science, including advanced machine learning, big data analytics, Semantic Web technologies, natural language processing, social media analysis, time series analysis, among others, for applications in economics and finance. In addition, it shows some successful applications of advanced data science solutions used to extract new knowledge from data in order to improve economic forecasting models. The book starts with an introduction on the use of data science technologies in economics and finance and is followed by thirteen chapters showing success stories of the application of specific data science methodologies, touching on particular topics related to novel big data sources and technologies for economic analysis (e.g. social media and news); big data models leveraging on supervised/unsupervised (deep) machine learning; natural language processing to build economic and financial indicators; and forecasting and nowcasting of economic variables through time series analysis. This book is relevant to all stakeholders involved in digital and data-intensive research in economics and finance, helping them to understand the main opportunities and challenges, become familiar with the latest methodological findings, and learn how to use and evaluate the performances of novel tools and frameworks. It primarily targets data scientists and business analysts exploiting data science technologies, and it will also be a useful resource to research students in disciplines and courses related to these topics. Overall, readers will learn modern and effective data science solutions to create tangible innovations for economic and financial applications.

This paper discusses the impact of the rapid adoption of artificial intelligence (AI) and machine learning (ML) in the financial sector. It highlights the benefits these technologies bring in terms of financial deepening and efficiency, while raising concerns about its potential in widening the digital divide between advanced and developing economies. The paper advances the discussion on the impact of this technology by distilling and categorizing the unique risks that it could pose to the integrity and stability of the financial system, policy challenges, and potential regulatory approaches. The evolving nature of this technology and its application in finance means that the full extent of its strengths and weaknesses is yet to be fully understood. Given the risk of unexpected pitfalls, countries will need to strengthen prudential oversight.

Opinion mining is a prevalent research issue in many domains. In the financial domain, however, it is still in the early stages. Most of the researches on this topic only focus on the coarse-grained market sentiment analysis, i.e., 2-way classification for bullish/bearish. Thanks to the recent financial technology (FinTech) development, some interdisciplinary researchers start to involve in the in-depth analysis of investors' opinions. These works indicate the trend toward fine-grained opinion mining in the financial domain. When expressing opinions in finance, terms like bullish/bearish often spring to mind. However, the market sentiment of the financial instrument is just one type of opinion in the financial industry. Like other industries such as manufacturing and textiles, the financial industry also has a large number of products. Financial services are also a major business for many financial companies, especially in the context of the recent FinTech trend. For instance, many commercial banks focus on loans and credit cards. Although there are a variety of issues that could be explored in the financial domain, most researchers in the AI and NLP communities only focus on the market sentiment of the stock or foreign exchange. This open access book addresses several research issues that can broaden the research topics in the AI community. It also provides an overview of the status quo in fine-grained financial opinion mining to offer insights into the futures goals. For a better understanding of the past and the current research, it also discusses the components of financial opinions one-by-one with the related works and highlights some possible research avenues, providing a research agenda with both micro- and macro-views toward financial opinions.

In this book readers will find technological discussions on the existing and emerging technologies across the different stages of the big data value chain. They will learn about legal aspects of big data, the social impact, and about education needs and requirements. And they will discover the business perspective and how big data technology can be exploited to deliver value within different sectors of the economy. The book is structured in four parts: Part I “The Big Data Opportunity” explores the value potential of big data with a particular focus on the European context. It also describes the legal, business and social dimensions that need to be addressed, and briefly introduces the European Commission’s BIG project. Part II “The Big Data Value Chain” details the complete big data lifecycle from a technical point of view, ranging from data acquisition, analysis, curation and storage, to data usage and exploitation. Next, Part III “Usage and Exploitation of Big Data” illustrates the value creation possibilities of big data applications in various sectors, including industry, healthcare, finance, energy, media and public services. Finally, Part IV “A Roadmap for Big Data Research” identifies and prioritizes the cross-sectorial requirements for big data research, and outlines the most urgent and challenging technological, economic, political and societal issues for big data in Europe. This compendium summarizes more than two years of work performed by a leading group of major European research centers and industries in the context of the BIG project. It brings together research findings, forecasts and estimates related to this challenging technological context that is becoming the major axis of the new digitally transformed business environment.

Based on interdisciplinary research into "Directional Change", a new data-driven approach to financial data analysis, Detecting Regime Change in Computational Finance: Data Science, Machine Learning and Algorithmic Trading applies machine learning to financial market monitoring and algorithmic trading. Directional Change is a new way of summarising price changes in the market. Instead of sampling prices at fixed intervals (such as daily closing in time series), it samples prices when the market changes direction ("zigzags"). By sampling data in a different way, this book lays out concepts which enable the extraction of information that other market participants may not be able to see. The book includes a Foreword by Richard Olsen and explores the following topics: Data science: as an alternative to time series, price movements in a market can be summarised as directional changes Machine learning for regime change detection: historical regime changes in a market can be discovered by a Hidden Markov Model Regime characterisation: normal and abnormal regimes in historical data can be characterised using indicators defined under Directional Change Market Monitoring: by using historical characteristics of normal and abnormal regimes, one can monitor the market to detect whether the market regime has changed Algorithmic trading: regime tracking information can help us to design trading algorithms It will be of great interest to researchers in computational finance, machine learning and data science. About the Authors Jun Chen received his PhD in computational finance from the Centre for Computational Finance and Economic Agents, University of Essex in 2019. Edward P K Tsang is an Emeritus Professor at the University of Essex, where he co-founded the Centre for Computational Finance and Economic Agents in 2002.

Supporting competitive business analysis of financial reports through the automated analysis and interpretation of their natural language sections, presents specific challenges including information that can be ambiguous, camouflaged, or tacitly hidden within the narrative. These sections present terminology and structural challenges for information extraction that require the application of linguistic and heuristic based domain modelling to identify the information requirement. This thesis investigates a modelling approach that incrementally builds the business analysts information requirement as a series of Semantic Paths grounded in domain linguistic and user heuristics. A Competitive Analysis Ontology (CAO) is defined to provide semantic representation of the information requirement necessary to drive linguistic analysis and information extraction. The evaluation of the CAO within the financial sub-domain of competitive analysis is investigated, through the development of the Analyst Work Bench (AWB), is presented. The AWB linguistically analyses a Form 10-Q’s disclosure sections, automatically populates the CAO and provides the analyst’s information requirement. The AWB leverages the CAO Semantic Paths for information search and extraction capability, to support an analyst perform a competitive analysis, with reduced manual effort. Evaluation based on design-science principles, use methods from information retrieval and information system success to determine CAO performance and usability. A controlled experiment that compares competitive analysis performance using the AWB, against its manual performed equivalent, reported a 37% performance increase using the AWB to identify relevant information. Usability evaluation further found that CAO use contributed to task structuring, and structured information provision in a manner that directly supported task performance.