Pub date: August 1, 2025
ISBN: 9787302697343
Rights: All Rights Available
284 p.p.
This book is a professional textbook designed to provide a systematic exposition of the deep integration of artificial intelligence technology with finance. Driven by the global wave of digital economy and national policy support, the financial industry is undergoing a profound transformation powered by AI, big data, and blockchain technologies. This work aims to bridge the current gap between financial theory and AI practice, offering readers an interdisciplinary knowledge framework that combines theoretical depth with practical value.
Focusing on the intersection of finance and artificial intelligence, the book helps readers understand how intelligent technologies can empower core financial processes—including data processing, risk pricing, and service innovation—while addressing practical challenges such as adapting algorithmic models to financial scenarios, handling the unique characteristics of financial data, and balancing model complexity with business interpretability.
The target audience for this textbook primarily includes undergraduate students in finance, financial engineering, and related disciplines, while also catering to computer science and applied mathematics students taking fintech electives. The content is carefully structured according to cognitive science principles, emphasizing a progressive knowledge building path from fundamental theories to engineering practice.
Chapter 1: Fundamental Principles of Financial Intelligence
Chapter Introduction
Learning Objectives
1.1 Overview and History of Artificial Intelligence
1.1.1 AI Overview
1.1.2 History of AI Development
1.2 Overview and Scenarios of Financial Intelligence
1.2.1 Overview of Financial Intelligence
1.2.2 Common Scenarios in Financial Intelligence
1.2.3 Common Technologies in Financial Intelligence
1.3 Practice and Directions of Financial Intelligence
1.3.1 Current State of Financial Intelligence Development
1.3.2 Challenges in Financial Intelligence
1.3.3 Future Directions for Financial Intelligence
1.4 Python Fundamentals
1.4.1 Python Installation
1.4.2 Common Data Types, Conditionals, Loops, and Functions
1.5 Machine Learning Model Evaluation
1.5.1 Overfitting and Underfitting
1.5.2 Bias-Variance Tradeoff
1.5.3 Evaluation Metrics for Regression Models
1.5.4 Hyperparameter Tuning in Machine Learning
Chapter Summary
Key Terms
Review Questions
Chapter 2: Fundamental Principles of Finance
Chapter Introduction
Learning Objectives
2.1 Financial Markets
2.1.1 Concepts and Functions of Financial Markets
2.1.2 Classification of Financial Markets
2.2 Empirical Asset Pricing
2.2.1 The Core Issue of Asset Pricing - Expected Stock Returns
2.2.2 Portfolio Analysis
2.2.3 Factor Investing
2.2.4 Chinese Factor Models
Chapter Summary
Key Terms
Review Questions
Chapter 3: Linear Methods in Financial Intelligence
Chapter Introduction
Learning Objectives
3.1 Overview of Linear Analysis Methods
3.1.1 Linear Models from an Econometrics Perspective
3.1.2 Linear Models from a Matrix Perspective
3.1.3 Loss Functions
3.2 Logistic Regression Algorithm
3.2.1 Classification Problems
3.2.2 Logistic Regression
3.3 Testing Anomaly Factors
3.3.1 Anomaly Factors
3.3.2 Statistical Testing of Anomaly Factors via Time-Series Regression
3.3.3 Testing Stock Characteristics and Future Returns: Fama-MacBeth Cross-Sectional Regression
Chapter Summary
Key Terms
Review Questions
Chapter 4: Linear Methods with Penalization
Chapter Introduction
Learning Objectives
4.1 Introduction to Penalized Linear Methods
4.2 Ridge Regression
4.3 LASSO
4.4 Elastic Net Regression
4.5 Case Study: Using LASSO for High-Frequency Trading
4.6 Hands-on: Monte Carlo Simulation
Chapter Summary
Key Terms
Review Questions
Chapter 5: Dimensionality Reduction Methods in Financial Intelligence
Chapter Introduction
Learning Objectives
5.1 Overview of Dimensionality Reduction Methods
5.2 Principal Component Analysis (PCA) Algorithm
5.2.1 PCA Principles
5.2.2 PCA Algorithm
5.2.3 PCA Code
5.3 Partial Least Squares (PLS) Algorithm
5.3.1 PLS Principles
5.3.2 PLS Algorithm
5.3.3 PLS Code
5.4 Instrumented Principal Component Analysis (IPCA) Algorithm
5.4.1 IPCA Model Principles
5.4.2 Constrained IPCA Model
5.4.3 Unconstrained IPCA Model
5.4.4 Extensions of the IPCA Model
5.5 Case Study: Measuring Investor Sentiment
5.5.1 Investor Sentiment
5.5.2 Index Construction Based on PCA
5.6 Hands-on Code and Analysis
5.6.1 Code
5.6.2 Improved Index Construction Based on PLS
Chapter Summary
Key Terms
Review Questions
Chapter 6: Cluster Analysis and Its Financial Applications
Chapter Introduction
Learning Objectives
6.1 Overview of Cluster Analysis
6.1.1 Concept of Cluster Analysis
6.1.2 Clustering Process
6.1.3 Requirements for Clustering Algorithms
6.1.4 Distance Metrics for Clustering Algorithms
6.2 K-Means Clustering Algorithm
6.2.1 K-Means Clustering Concept
6.2.2 K-Means Clustering Code
6.3 Hierarchical Clustering Algorithm
6.3.1 Hierarchical Clustering Concept
6.3.2 Hierarchical Clustering Code
6.4 Density-Based Clustering Algorithm
6.4.1 DBSCAN Algorithm Concept
6.4.2 DBSCAN Algorithm Code
6.5 Application of Cluster Analysis in Financial Customer Segmentation
Chapter Summary
Key Terms
Review Questions
Chapter 7: Tree-Based Methods in Financial Intelligence
Chapter Introduction
Learning Objectives
7.1 Overview and Application Scenarios of Tree-Based Methods
7.2 Regression Trees
7.2.1 Regression Tree Principles
7.2.2 Regression Tree Algorithm
7.2.3 Regression Tree Code
7.3 Ensemble Learning and Random Forest Algorithm
7.3.1 Ensemble Learning and Random Forest Principles
7.3.2 Random Forest Algorithm
7.3.3 Random Forest Code
7.4 Gradient Boosting Regression Tree (GBRT) Algorithm
7.4.1 GBRT Principles
7.4.2 GBRT Algorithm
7.4.3 GBRT Code
Chapter Summary
Key Terms
Review Questions
Chapter 8: Fully Connected Neural Network Models in Financial Intelligence
Chapter Introduction
Learning Objectives
8.1 Overview of Artificial Neural Network Methods
8.2 Activation Functions
8.2.1 ReLU Activation Function
8.2.2 Sigmoid Activation Function
8.2.3 Tanh Activation Function
8.3 Optimization Algorithms
8.3.1 Gradient Descent
8.3.2 Mini-batch Stochastic Gradient Descent
8.3.3 Momentum
8.3.4 AdaGrad Algorithm
8.3.5 RMSProp Algorithm
8.3.6 Adam Algorithm
8.4 Model Training
8.4.1 Weight Penalty
8.4.2 Dropout
8.4.3 Early Stopping
8.4.4 Batch Normalization
8.5 Fully Connected Neural Network Code
8.6 Case Study: Stock Selection Model Using Fully Connected Neural Networks Based on Firm Characteristics
8.7 Hands-on Code Analysis: Monte Carlo Simulation
Chapter Summary
Key Terms
Review Questions
Chapter 9: Autoencoder Models in Financial Intelligence
Chapter Introduction
Learning Objectives
9.1 Overview of Autoencoder (AE) Methods
9.2 AE Code
9.3 Conditional AE and Factor Pricing Models in Finance
9.4 Conditional AE Code
9.5 Monte Carlo Simulation
Chapter Summary
Key Terms
Review Questions
Chapter 10: Convolutional Neural Network Models in Financial Intelligence
Chapter Introduction
Learning Objectives
10.1 Overview of CNN Methods
10.2 CNN Algorithm
10.2.1 Convolutional Layer
10.2.2 Pooling Layer
10.3 CNN Code
10.4 Case Study: Candlestick Chart Recognition and Stock Return Prediction
Chapter Summary
Key Terms
Review Questions
Chapter 11: Recurrent Neural Network Models in Financial Intelligence
Chapter Introduction
Learning Objectives
11.1 RNN Model Basics
11.1.1 RNN Model Overview
11.1.2 Core Principles of RNN
11.1.3 Comparing RNN with Other Neural Networks
11.2 RNN Variants and Training
11.2.1 Implementing RNN Models in Python
11.2.2 RNN Training Process and Parameter Tuning
11.3 Applications of RNN in Financial Intelligence
Case: RNN Models and the Efficient Market Hypothesis
Chapter Summary
Key Terms
Review Questions
Chapter 12: Generative Adversarial Network Models in Financial Intelligence
Chapter Introduction
Learning Objectives
12.1 GAN Model Basics
12.1.1 GAN Model Overview
12.1.2 Core Components of GAN
12.2 GAN Model Training and Optimization
12.2.1 Implementing GAN Models in Python
12.2.2 GAN Parameter Tuning and Stability Issues
12.3 Applications of GAN in Financial Intelligence
Case: GAN and SDF Estimation
References
Chapter Summary
Key Terms
Review Questions
Chapter 13: Natural Language Processing Methods in Financial Intelligence
Chapter Introduction
Learning Objectives
13.1 Overview and Application Scenarios of Text Analysis
13.1.1 Overview of Text Analysis
13.1.2 Application Scenarios of Text Analysis
13.1.3 General Workflow for Text Data Processing
13.2 Morphology and Word Segmentation
13.2.1 Morphology
13.2.2 Word Segmentation
13.2.3 Word Segmentation Code
13.3 Bag-of-Words and Word Embedding Models
13.3.1 Bag-of-Words Model
13.3.2 Word Embedding Models
13.3.3 Word Embedding Model Code
13.4 TF-IDF Algorithm
13.4.1 Overview of Keyword Extraction
13.4.2 TF-IDF Algorithm
13.4.3 TF-IDF Algorithm Code
13.5 Topic Models
13.5.1 Overview of Topic Models
13.5.2 LDA Algorithm
13.5.3 LDA Code
Chapter Summary
Key Terms
Review Questions
Chapter 14: Reinforcement Learning Algorithms in Financial Intelligence
Chapter Introduction
Learning Objectives
14.1 Reinforcement Learning Basics
14.1.1 Overview of Reinforcement Learning
14.1.2 Core Components of Reinforcement Learning
14.1.3 Reinforcement Learning vs. Other Learning Methods
14.2 Reinforcement Learning Algorithms and Training
14.2.1 Major Reinforcement Learning Algorithms
14.2.2 Python Implementation Case Study
14.3 Applications of Reinforcement Learning
Case: Reinforcement Learning in Financial Intelligence
References
Chapter Summary
Key Terms
Review Questions
Chapter 15: Blockchain Methods in Financial Intelligence
Chapter Introduction
Learning Objectives
15.1 Overview and Application Scenarios of Blockchain Technology
15.1.1 History of Blockchain Technology
15.1.2 Blockchain Classification
15.1.3 Application Scenarios of Blockchain Technology
15.2 Encryption Algorithms and Consensus Mechanisms in Blockchain
15.2.1 Common Encryption Algorithms
15.2.2 Common Consensus Mechanisms
15.2.3 Economics Behind Consensus Mechanisms
15.2.4 Generating Bitcoin Public and Private Keys in Python
15.3 Blockchain Technology and Smart Contracts
15.3.1 Smart Contract Technology
15.3.2 Smart Contracts and Digital CNY (e-CNY)
15.4 Blockchain Applications in Financial Scenarios
Case: The Stablecoin DAI on the Ethereum Public Chain
Chapter Summary
Key Terms
Review Questions
Chapter 16: Financial Intelligence Applications in Industry
Chapter Introduction
Learning Objectives
16.1 Overview of Financial Intelligence Applications in Industry
16.2 Machine Learning for Asset Price Prediction
16.2.1 Principles of ML-based Asset Price Prediction
16.2.2 Practice in US Stock Markets
16.2.3 Practice in Chinese Stock Markets
16.3 Text Analysis for Asset Price Prediction
16.4 Text Analysis Applications in Green Finance
Chapter Summary
Key Terms
Review Questions
Chapter 17: FinTech Regulation and RegTech
Chapter Introduction
Learning Objectives
17.1 Overview of FinTech Regulation and RegTech
17.2 Regulatory Cases Across Fintech Sectors
17.3 Regulatory Technology (RegTech)
Chapter Summary
Key Terms
Review Questions
