This edited book explores the unique risks, opportunities, challenges, and societal implications associated with big data developments within the field of finance. While the general use of big data has been the subject of frequent discussions, this book will take a more focused look at big data applications in the financial sector. With contributions from researchers, practitioners, and entrepreneurs involved at the forefront of big data in finance, the book discusses technological and business-inspired breakthroughs in the field. The contributions offer technical insights into the different applications presented and highlight how these new developments may impact and contribute to the evolution of the financial sector. Additionally, the book presents several case studies that examine practical applications of big data in finance. In exploring the readiness of financial institutions to adapt to new developments in the big data/artificial intelligence space and assessing different implementation strategies and policy solutions, the book will be of interest to academics, practitioners, and regulators who work in this field.
Author(s): Thomas Walker, Frederick Davis, Tyler Schwartz
Publisher: Palgrave Macmillan
Year: 2022
Language: English
Pages: 282
City: Cham
Preface
Acknowledgments
Contents
Notes on Contributors
List of Figures
List of Tables
Introduction
Big Data in Finance: An Overview
1 Introduction
2 Overview of Content
2.1 Part I: Big Data in the Financial Markets
2.2 Part II: Big Data in Financial Services
2.3 Part III: Case Studies and Applications
References
Big Data in the Financial Markets
Alternative Data
1 Introduction
2 Characteristics of Alternative Data
2.1 Less Commonly Used by Market Participants
2.2 Tend to Be More Costly to Collect and Purchase
2.3 Typically Outside of Financial Markets
2.4 Tend to Lack Historical Data
2.5 More Challenging to Use
3 Catalysts of the Growth in Alternative Data
4 Sources of Alternative Data
5 Types of Alternative Data
5.1 Text Data
5.2 Job Postings and Other Economic Activity Indicators
5.3 Mandatory Disclosures
5.4 Social Media Data: Use Cases, Methods, Applications
5.5 Transaction Data
5.6 Satellite Imagery and Weather Data
6 Processing Alternative Data
7 Evaluating Alternative Data
8 Conclusion
References
An Algorithmic Trading Strategy to Balance Profitability and Risk
1 Introduction
2 Algorithmic Trading: Concept, Methods, and Influence
3 Proposed AT Strategy
4 Empirical Evidence of Proposed AT Strategies
4.1 Empirical Analysis
5 Comparison of Proposed AT Strategy with Other Benchmarks
5.1 Empirical Evidence of AT Strategy Using IBEX-35 Exchange
5.2 Evidence of AT Strategy Using Fictional Data and Other AT Strategies
6 Discussion and Applicability of Big Data to Proposed AT Strategy
7 Conclusion
References
High-Frequency Trading and Market Efficiency in the Moroccan Stock Market
1 Introduction
2 Literature Review
3 Methodology and Data
3.1 Methodology
3.2 Data
4 Results
5 Conclusion
References
Ensemble Models Using Symbolic Regression and Genetic Programming for Uncertainty Estimation in ESG and Alternative Investments
1 Introduction
2 Background
2.1 Stocks and ETFs
2.1.1 Levi Strauss
2.1.2 British American Tobacco (BATS)
2.1.3 How ETFs Integrate ESG Factors into Stock Selections
3 Modeling and Data Collection
3.1 Modeling
3.1.1 Symbolic Regression (SR)
3.1.2 Symbolic Regression Versus Regression Models
3.1.3 Trustable Model Ensembles
3.1.4 Estimating (and Reducing) Uncertainty
3.2 Data Collection
3.2.1 Publicly Traded Private Equity Stocks
3.2.2 Sustainable ETFs
4 Results
4.1 Publicly Traded Private Equity Stocks
4.2 Sustainable ETFs
5 Discussion
5.1 Publicly Traded Private Equity Stocks
5.2 Sustainable ETFs
5.3 Ensemble Models Using Big Data
6 Conclusion
6.1 Publicly Traded Private Equity Stocks
6.2 Sustainable ETFs
Appendix
References
Big Data in Financial Services
Consumer Credit Assessments in the Age of Big Data
1 Introduction
2 Overview of Traditional Credit Assessment Data and Techniques
3 FinTech Lenders and Data Evolution
3.1 P2P Lending and Resulting Data Creation
3.2 The Expanding Scope of Alternative Data
4 Advancements in Methodologies and Technologies
4.1 Common Classification Methodologies in ML
4.2 Model Performance and Evaluation
5 Challenges, Biases, and Ethics
6 Conclusions and Areas for Future Research
References
Robo-Advisors: A Big Data Challenge
1 Introduction
2 Robo-Advisor Features, Benefits, and Drawbacks
2.1 Generalities and Recent Trends in the Financial Industry
2.2 Robo-Advisor Benefits
2.3 Robo-Advisor Drawbacks
3 Big Data and Artificial Intelligence in Robo-Advisory
3.1 Humanization Inspired by Artificial Intelligence
3.2 Big Data for Robo-Advisor Customization
3.3 Opening the Black Box
4 Conclusion
References
Bitcoin: Future or Fad?
1 Introduction
2 Is Bitcoin the Future of Payment Systems?
2.1 Bitcoin as a Cash Proxy
2.1.1 Stablecoins
2.2 Bitcoin vs Gold: A Store of Value?
2.3 Bitcoin: Investment and Diversification Role
2.3.1 Bitcoin: Political Uncertainty and Dictatorial Regimes
2.4 Is Bitcoin a Collectible Asset?
3 Discussion
3.1 What is Bitcoin's Real Contribution: Cryptocurrencies, Big Data, and Blockchain Technology
3.2 Government Regulations
4 Concluding Thoughts
References
Culture, Digital Assets, and the Economy: A Trans-National Perspective
1 Introduction
2 Literature Review
3 Methodology
3.1 Hypothesis Development
3.2 Data, Variables, and Modeling
4 Results
4.1 Financial Institutions and the Use of Digital Assets
4.2 The Role of Culture in the Use of Digital Assets
4.2.1 Evidence from Hofstede Culture Dimensions
4.2.2 Evidence from Alternative Measures of Culture
5 Conclusion
Appendix
References
Case Studies and Applications
Islamic Finance in Canada Powered by Big Data: A Case Study
1 Introduction
2 Methods
3 Deep Learning Models
3.1 The Building Blocks of Deep Learning
3.2 Deep Learning Models for Credit Scoring and Risk Prediction
3.3 Deep Learning Models for Processing Sequential Data
4 How Deep Learning Is (and Can Be) Used in Credit Unions
4.1 Deep Learning Models for Consumer Risk Prediction
4.2 Deep Learning Models for Financial Forecasting
5 Conclusions
References
Assessing the Carbon Footprint of Cryptoassets: Evidence from a Bivariate VAR Model
1 Introduction
2 Literature Review
3 Data Description
4 Empirical Methodology
4.1 Causality Tests
4.2 Impulse–Response Analysis
5 Environmental Impact of Cryptoassets
6 Concluding Remarks
References
A Data-Informed Approach to Financial Literacy Enhancement Using Cognitive and Behavioral Analytics
1 Introduction
2 Related Work
2.1 Defining Financial Literacy
2.2 Associated Factors
3 Learning About Learners: Analyzing Participant Behavior in a Large-Scale Financial Literacy Program
3.1 Financial Literacy Training Boosts Financial Knowledge, Confidence, and Intention
3.2 Heterogeneities in Impact of Financial Literacy Trainings
3.3 Factors Associated with Financial Intention
3.4 Generating Profiles of IFL's Learners Using Cluster Analysis
4 Recommendations for a Data-Informed Financial Literacy Program
4.1 Expanding Financial Literacy Touchpoints on Mobile and Web
4.2 Development of a Psychologically Enhanced Learner Profile for Improved Personalization
4.3 Continuous Evaluation of Financial Literacy Programs and Policies
4.4 Increased Focus on Specific Population Groups
5 Conclusion
References
Index
