Artificial Intelligence for Capital Market throws light on the application of AI/ML techniques in the financial capital markets. This book discusses the challenges posed by the AI/ML techniques as these are prone to "black box" syndrome. The complexity of understanding the underlying dynamics for results generated by these methods is one of the major concerns which is highlighted in this book.
Features
Showcases artificial intelligence in finance service industry
Explains credit and risk analysis
Elaborates on cryptocurrencies and blockchain technology
Focuses on the optimal choice of asset pricing model
Introduces testing of market efficiency and forecasting in the Indian stock market
This book serves as a reference book for academicians, industry professionals, traders, finance managers and stock brokers. It may also be used as textbook for graduate level courses in financial services and financial analytics.
Author(s): Syed Hasan Jafar, Hemachandran K., Hani El-Chaarani, Sairam Moturi, Neha Gupta
Publisher: CRC Press/Chapman & Hall
Year: 2023
Language: English
Pages: 182
City: Boca Raton
Cover
Half Title
Title Page
Copyright Page
Contents
Preface
About the Editors
Contributors
CHAPTER 1. Artificial Intelligence in the Financial Services Industry
1.1 Introduction
1.2 Artificial Intelligence
1.2.1 Types of AI
1.2.2 Subcategories of AI
1.3 Applications of AI in Financial Services
1.3.1 Robo-Advisory
1.3.2 Predictions
1.3.3 Fintech
1.3.4 Risk Management
1.3.5 Chatbot Technology
1.3.6 Ethical AI
1.3.7 Bank Lending Operations
1.3.8 Credit Scoring
1.3.9 Debt Collection
1.3.10 Regulatory Compliance
1.3.11 Personalized Banking
1.3.12 Cybersecurity
1.4 Issues with AI in the Finance Industry
1.4.1 Impact on Trading Based on Algorithms
1.4.2 Assuring "Data Privacy" and "Information Security"
1.4.3 Assuring "Governance" and "Trust"
1.4.4 Risk of Relevant Laws and Regulations
1.4.5 Risk of Data Acquisition, and Leakage
1.4.6 Security Risks
1.5 Future Trends of AI in Finance
1.5.1 Use of Synthetic Data
1.5.2 Creating AI Legislation and Regulations
1.5.3 Increasing the Effectiveness of Financial Market Risk Mitigation
1.6 Conclusion
Acknowledgement
Notes
References
CHAPTER 2. Machine Learning and Big Data in Finance Services
2.1 Introduction
2.2 Big Data Characteristics and Current Works in the Finance Services
2.2.1 Data Management
2.2.2 Big Data Characteristics
2.2.3 Big Data Processing
2.2.4 Big Data and Financial Applications
2.3 Machine Learning
2.3.1 Definition and Characteristics
2.3.2 ML Types
2.3.2.1 Supervised Learning
2.3.2.2 Unsupervised Learning
2.3.2.3 Semi-supervised Learning
2.3.2.4 Reinforcement Learning
2.3.3 ML in Finance Services
2.3.3.1 Financial Monitoring Systems
2.3.3.2 Investment Prediction Systems
2.3.3.3 Process Automation Systems
2.3.3.4 Transaction Analysis and Fraud Detection Solutions
2.3.3.5 Financial Advisory Solutions
2.3.3.6 Credit Scoring Solutions
2.3.3.7 Customer Service Solutions
2.3.3.8 Marketing Solutions
2.3.3.9 Customer Sentiment Analysis Solutions
2.3.3.10 Algorithmic Trading System
2.4 Challenges for the Integration of Big Data and ML in Finance Services
2.5 Conclusion
References
CHAPTER 3. Artificial Intelligence in Financial Services: Advantages and Disadvantages
3.1 Introduction
3.2 Overview of AI
3.3 AI Applications in the Financial Sector
3.3.1 AI and Customer Services and Support
3.3.2 AI and Bank Failure Prediction
3.3.3 AI and Financial Inclusion
3.3.4 AI and Credit Risk Management
3.4 Advantages and Disadvantages of AI Applications in the Financial Sector
3.4.1 Advantages of AI Applications in the Banking Sector
3.4.2 Disadvantages of AI Applications in the Banking Sector
3.5 Summary and Recommendations
References
CHAPTER 4. Upscaling Profits in Financial Market
4.1 Introduction
4.2 Literature Review
4.3 Proposed Methodology
4.3.1 Prediction Module
4.3.2 Trading Strategy Module
4.4 Implementation Details
4.4.1 Dataset
4.4.2 Tools
4.4.3 Evaluation Metrics
4.5 Result and Analysis
4.6 Conclusion and Future Work
References
CHAPTER 5. Credit and Risk Analysis in the Financial and Banking Sectors: An Investigation
5.1 Introduction
5.1.1 Objective of the Study
5.2 Literature Review
5.3 Methodology of Research
5.4 Data Analysis
5.4.1 Interpretation 1
5.4.2 Interpretation 2
5.4.3 Interpretation 3
5.4.4 Interpretation 4
5.4.5 Interpretation 5
5.4.6 Interpretation 6
5.4.7 Interpretation 7
5.5 Conclusion
References
CHAPTER 6. Cryptocurrencies and Blockchain Technology Applications
6.1 Introduction
6.2 Blockchain Technology, Explained
6.2.1 How Does It Work?
6.2.2 The Evolution of Blockchain
6.2.3 Permissionless and Permissioned Blockchain
6.3 Blockchain Technology Applications
6.3.1 Cryptocurrencies
6.3.2 Financial Markets
6.3.3 Banking Sector
6.4 Benefits and Challenges
6.4.1 Benefits of Blockchain
6.4.2 Challenges Faced by Blockchain
6.5 Conclusion, Recommendations, and Future Work
References
CHAPTER 7. Machine Learning and the Optimal Choice of Asset Pricing Model
7.1 Introduction
7.2 Empirical Asset Pricing Models
7.2.1 Overview and Rationale
7.2.2 The CAPM
7.2.2.1 CAPM Limitations
7.2.3 Multifactor Models
7.2.3.1 APT
7.2.3.1.1 The Limitations of APT
7.2.3.2 Fama-French 3 and 5 Factor Models
7.2.3.3 Fama-French 3 and 5 Models Limitations
7.2.4 Discussion
7.3 Machine Learning in Asset Pricing
7.3.1 Machine Learning: Overview
7.3.2 The Case for Machine Learning in Asset Pricing
7.3.2.1 Machine Learning and MPT
7.4 Machine Learning Methods in Asset Pricing
7.4.1 Penalized Linear Regression
7.4.1.1 Statistical Overview
7.4.1.2 Application in Asset Pricing
7.4.2 Regression Trees
7.4.2.1 Statistical Overview
7.4.2.1.1 Regression Tree Boosting
7.4.2.1.2 Random Forest Regression
7.4.2.2 Application in Asset Pricing
7.4.3 Support Vector Regression
7.4.3.1 Statistical Overview
7.4.3.2 Application in Asset Pricing
7.4.4 Markov Switching Models
7.4.4.1 Statistical Overview
7.4.4.2 Application in Asset Pricing
7.5 Artificial Neural Networks in Asset Pricing
7.5.1 ANNs: Overview
7.5.2 Feed-Forward Neural Networks
7.5.3 Recurrent Neural Networks
7.5.4 Ensemble Neural Networks
7.5.5 NNs in Asset Pricing
7.6 Limitations
7.6.1 Limitations of Machine Learning
7.6.1.1 Machine Learning and Regulatory Environment
7.6.2 Limitations of This Study
7.7 Conclusions
Notes
Bibliography
CHAPTER 8. Testing for Market Efficiency Using News-Driven Sentiment: Evidence from Select NYSE Stocks
8.1 Introduction
8.2 Literature Review
8.3 Research Methodology
8.3.1 Correlation Coefficient
8.3.2 Granger Causality Test
8.4 Findings and Discussion
8.5 Implications and Future Research
8.6 Conclusion
References
CHAPTER 9. Comparing Statistical, Deep Learning, and Additive Models for Forecasting in the Indian Stock Market
9.1 Introduction
9.2 Literature Review
9.3 Methodology
9.3.1 Statistical Time-Series Models
9.3.2 Long-Short Term Memory Networks
9.3.3 The FbProphet Algorithm
9.3.4 Evaluation Measures
9.4 Empirical Analysis and Results
9.4.1 Data
9.4.2 Augmented Dickey Fuller Test and Stationarity
9.4.3 Training and Testing Splits
9.4.4 Model Specifications
9.4.5 Results
9.5 Conclusion
References
CHAPTER 10. Applications and Impact of Artificial Intelligence in the Finance Sector
10.1 Introduction
10.2 Literature Review
10.3 Applications of AI in Finance
10.3.1 Personal Finance
10.3.2 Consumer Finance
10.3.3 Corporate Finance
10.4 Risk Assessment
10.5 Insurance Claim
10.6 Trading and Share Market
10.7 Discussion and Future Scope
10.8 Conclusion
References
Index
