Machine Learning for Finance: Beginner’s guide to explore machine learning in banking and finance

Cover Page
Title Page
Copyright Page
Dedication Page
About the Author
About the Reviewer
Acknowledgement
Preface
Errata
Table of Contents
1. Introduction
    Introduction
    Structure
    Objective
    How machines are taught
    Factors contributing to the success of machine learning
    Machine learning and artificial intelligence
    Machine learning and deep learning
    Machine learning and statistics
    Machine learning and data mining
        What’s the difference?
    Machine learning in finance
    Importance of machine learning in finance
    Robo-warning
    How to utilize machine learning in finance
    Utilize outsider machine learning arrangements
    Development and combination
    How is machine learning used today
        Financial services
    Conclusion
2. Naive Bayes, Normal Distribution, and Automatic Clustering
    Introduction
    Structure
    Objective
    Naive Bayes
        Bayesian classification
        Strengths, weaknesses, and parameters of the Naive Bayes algorithm
        Applications of the Naive Bayes algorithm
            Recommendation systems
    Normal distribution
    Automatic cluster detection in data mining
        Searching for simplicity islands
            Light of the moon, bright star
        Gaussian model
    Application of machine learning in cybersecurity
        Spam detection
        Phishing page detection
        Malware detection
            DoS and DDoS attack detection
        Anomaly detection
    Conclusion
3. Machine Learning for Data Structuring
    Introduction
    Structure
    Objective
    Data structuring
    The future of big data
    Structured and unstructured data
    Conclusion
4. Parsing Data Using NLP
    Introduction
    Structure
    Objective
    Uses of NLP
    Key advantages of NLP
    Data handling in NLP
    NLP applications
        Talent recruitment
        Voice assistants
        Health care
        Survey analysis
        Grammar checkers
        Email filtering
        Social media monitoring
        Online search autocomplete and autocorrect
    Conclusion
5. Computer Vision
    Introduction
    Structure
    Objective
    Computer vision application
    Neural networks in computer vision
        Activation function
        Data preprocessing
        Weight initialization
        Introduction to CNN
            Convolutional layers
            Pooling layers
            Fully connected layers
    Overview of computer vision
    Image recognition
    Biometric recognition
    Software vulnerabilities
    Conclusion
6. Neural Network, GBM, and Gradient Descent
    Introduction
    Structure
    Objective
    Working of neural networks
    Types of neural networks in AI
        Feed-forward neural networks
        Recurrent neural networks
        Convolutional neural networks (CNNs)
        Modular neural networks
    Benefits of using artificial neural networks
    Gradient boosting algorithms
        GBM
            Light GBM
            XGBoost
            CatBoost
        Gradient descent
    Conclusion
7. Sequence Modeling
    Introduction
    Structure
    Objective
    Word embedding
    Feed-forward neural network algorithm
    Convolutional neural network algorithm
    Recurrent neural networks (RNN) algorithm
    Conditional random field (CRF) algorithm
    Modeling procedure
        Feature engineering and selecting a model
        Training the model
        Validating the model
        Predicting new observations
    Conclusion
8. Reinforcement Learning for Financial Markets
    Introduction
    Structure
    Objective
    Problem types in machine learning
    Identifying key predictors (data reduction)
    Learning from experience (reinforcement learning)
        Fundamentals of reinforcement learning
            Agent
        Algorithms for control learning
        Applications of reinforcement learning
    Reinforcement learning algorithms
    Types of reinforcement learning
    Applications of reinforcement learning in real life
    Conclusion
9. Finance Use Cases
    Introduction
    Structure
    Objective
    Technology and finance
    Automation
        You might not hear the robots coming
        FinTech: Robocalypse comes to finance
    The impact of FinTech
    Guidelines to live by
    Innovative technologies
        AI/robotics including chatbot
        Cognitive computing
        Blockchain in the banking industry
        What is Blockchain?
        First blockchain user in the world: Australian Securities Exchange
        Internet of things (IoT) in banking
        Bank of America: Big data projects
        Voice biometrics
    Digital bank
    AI as a strategy at the top level
        Cost of investing in AI
        Crucial leadership involvement
        Inorganic growth
    Development status of different AI technologies
    Risk management
    Fraud detection and prevention
    Improving the truth of financial rules and designs
    Trading
    AI in banking
    Conclusion
10. Impact of Machine Learning on FinTech
    Introduction
    Structure
    Objective
    Overview of FinTech companies
    Impact of technology
    Challenges
    Conclusion
11. Machine Learning in Finance
    Introduction
    Structure
    Objective
    Machine learning use cases in banking
    Security
    Guaranteeing and credit scoring
    Algorithmic exchanging
    Robo-advisors
    Utilize outsider machine learning arrangements
    Applications of machine learning
    Current financial applications
        Portfolio management
        Algorithm trading
        Detecting fraud
        Insurance or credit insurance
    Machine learning and cryptocurrencies
        Day trading with machine learning
    Conclusion
12. eKYC and Anti-Fraud Policy
    Introduction
    Structure
    Objective
    Big data analytics: True Buzzword of today
    How criminals obtain information for online banking
    Common ways in which information can be stolen
        Retail stores or restaurants
        Online portals
        Hacked mail accounts
    ATMs
        Pickpockets and thieves
        Employee records
        Fake calls
        Social media
    Security measures
        Some tips on card security
        Security tips for Internet banking
    Conclusion
13. Uses of Data Mining and Data Visualization
    Introduction
    Structure
    Objective
    Data visualization
    Data mining
    Future health care
    Education
    Customer relationship management
    Criminal investigation
    Fraud detection
    Customer segmentation
    Intrusion detection
    Lie detection
    Conclusion
14. Advantages and Disadvantages of Machine Learning
    Introduction
    Structure
    Objective
    Advantages
        Identifies patterns
        Improves efficiency
        Completes specific tasks
        Helps machines adapt to the changing environment
        Helps machines handle large data sets
    Disadvantages
        Concepts involved in machine learning
            Statistics
            Brain modeling
            Adaptive control theory
            Psychological modeling
            AI
            Evolutionary models
    Conclusion
15. Applications of Machine Learning in Other Industries
    Introduction
    Structure
    Objective
    General applications of machine learning
    Conclusion
16. Ethical Considerations in Artificial Intelligence
    Introduction
    Structure
    Objective
    Loss of jobs
    Inequality
    Humanity
    Disinformation
    Artificial intelligence and crime
    Racist robots
    Artificial intelligence vs. humans
    Conclusion
17. Artificial Intelligence in Banking
    Introduction
    Structure
    Objective
    Fraud detection
    Cost cutting
    Customer service
    Risk management
    Internet banking
    Conclusion
18. Common Machine Learning Algorithms
    Introduction
    Structure
    Objective
    Regression
        Linear regression
        Logistic regression
    k-means clustering
        Three steps of the k-means algorithm
        What does k mean?
        Distance and similarity
    KNN algorithm
        How does KNN work?
        Preparing your training data for KNN
            Final remarks
    Principal component analysis (PCA) algorithm
    Polynomial fitting and least squares algorithm
    Forced linear regression algorithm
    Support vector machine (SVM) algorithm
    Conditional random fields (CRFs) algorithm
    Decision tree algorithm
    Conclusion
19. Frequently Asked Questions
    Conclusion
    Approaching a machine learning problem
    Humans in the loop
    Testing production systems
    Next step
    Machine learning packages
    Where do we go from here?
Index