[PART 01] Data Science Fundamentals

▣ Chapter 1: Understanding Data
1.1 Definition and types of data
___1.1.1 Data Types
___1.1.2 Data Attributes
1.2 Data Analysis
___1.2.1 Statistical Modeling
___1.2.2 Data Analysis Process
___1.2.3 Data Analysis Example
1.3 Data Visualization
___1.3.1 Types of visualization
___1.3.2 Visualization Principles
1.4 Exploratory Data Analysis
___1.4.1 Exploratory Data Analysis Checklist
___1.4.2 Example of Exploratory Data Analysis

▣ Chapter 2: Basics of Machine Learning
2.1 Machine Learning Concepts
___2.1.1 Business Goals and Implementation Considerations for Machine Learning
___2.1.2 Defining and considering problems that can be solved with machine learning
2.1 Machine Learning Principles
___2.1.1 Forward propagation
___2.2.2 Activation function
___2.2.3 Loss function
___2.2.4 Optimization Algorithm
___2.2.5 Backpropagation
2.3 Model Performance Improvement and Evaluation
___2.3.1 Overfitting and Underfitting
___2.3.2 Normalization Techniques
___2.3.4 Model Evaluation Metrics
___2.3.5 Model Selection and Hyperparameter Tuning
2.4 Examples of Machine Learning Model Applications
___2.4.1 Major approaches to machine learning
___2.4.2 Machine Learning Application Cases
___2.4.3 Considerations when applying the model

▣ Chapter 3: The Core of Deep Learning
3.1 Basic Neural Network Model
___3.1.1 Multilayer Perceptron
___3.1.2 Convolutional Neural Networks
___3.1.3 Recurrent Neural Networks
3.2 Generative and Representation Learning Models
___3.2.1 Autoencoder
___3.2.2 Generative Adversarial Networks
3.3 Domain-Specific Neural Network Models
___3.3.1 Graph Neural Networks
___3.3.2 Deep Q-network
3.4 Latest deep learning models
___3.4.1 Transformer
___3.4.2 Diffusion Model
___3.4.3 Large-Scale Language Models
___3.4.4 MoE Model

▣ Chapter 4: Deep Learning Applications
4.1 Natural Language Processing
___4.1.1 Data Preprocessing
___4.1.2 Model Architecture
___4.1.3 Model Training and Evaluation
___4.1.4 Core Model
___4.1.5 Required Papers
___4.1.6 Key Libraries and Tools
4.2 Audio Processing
___4.2.1 Data Preprocessing
___4.2.2 Model Architecture
___4.2.3 Model Training and Evaluation
___4.2.4 Core Model
___4.2.5 Required Papers
___4.2.6 Key Libraries and Tools
4.3 Computer Vision
___4.3.1 Data Preprocessing
___4.3.2 Model Architecture
___4.3.3 Model Training and Evaluation
___4.3.4 Core Model
___4.3.5 Required Papers
___4.3.6 Key Libraries and Tools
4.4 Reinforcement Learning
___4.4.1 Data Preprocessing
___4.4.2 Model Architecture
___4.4.3 Model Training and Evaluation
___4.4.4 Core Model
___4.4.5 Required Papers
___4.4.6 Key Libraries and Tools
4.5 Recommendation System
___4.5.1 Data Preprocessing
___4.5.2 Model Architecture
___4.5.3 Model Training and Evaluation
___4.5.4 Core Model
___4.5.5 Required Papers
___4.5.6 Key Libraries and Tools
4.6 Data Science Roadmap
___4.6.1 Natural Language Processing
___4.6.2 Audio Processing
___4.6.3 Computer Vision
___4.6.4 Reinforcement Learning
___4.6.5 Recommendation System
___4.6.6 Extended Technology Stack

[PART 02] Practical Data Science

▣ Chapter 5: Data Engineering
5.1 Data Collection
___5.1.1 Data Collection Method
___5.1.2 Data Collection Pipeline
___5.1.3 Considerations in Pipeline Design
5.2 Data Preprocessing
___5.2.3 Data Cleaning
___5.2.2 Data Conversion
___5.2.3 Feature Engineering
___5.2.4 Handling Data Imbalance
___5.2.5 Data Preprocessing Example
5.3 Data Governance
___5.3.1 Data Governance Components
___5.3.2 Data Governance Tools
___5.3.3 Timing of Data Governance Tool Introduction

▣ Chapter 6: Data Storage and Design
6.1 Data Storage and Management
___6.1.1 Relational Database Management System
___6.1.2 NoSQL
___6.1.3 Vector Database
___6.1.4 Strategies for Maintaining Data Consistency and Integrity
6.2 Data Architecture Patterns
___6.2.1 Data Storage and Management Architecture
___6.2.2 Data Modeling Techniques
___6.2.3 OLAP and OLTP Systems
___6.2.4 Cloud-based data warehouse
6.3 Data Pipeline Design
___6.3.1 ETL and ELT
___6.3.2 Design principles for data collection, transformation, and storage stages
___6.3.3 Data Pipeline Design Considerations
___6.3.4 Optimizing Data Pipelines in Distributed Data Environments

▣ Chapter 7: Model Operation and Management
7.1 API Design Principles
___7.1.1 RESTful API
___7.1.2 RESTful API Design and Implementation
___7.1.3 Introduction to GraphQL
___7.1.4 API Gateway Roles and Functions
7.2 Model Deployment
___7.2.1 Criteria for selecting a model deployment environment
___7.2.2 Model Deployment Methods and Scenarios
___7.2.3 Model Versioning and Rollback Strategies
7.3 Model Performance Monitoring
___7.3.1 Model Monitoring and Performance Analysis
___7.3.2 Model Drift Detection Methods
___7.3.3 Model Retraining Strategy
7.4 CI/CD and MLOps
___7.4.1 CI/CD Pipeline
___7.4.2 MLOps
___7.4.3 MLOps Platform
___7.4.4 MLOps Pipeline Design and Construction Strategy

▣ Chapter 8: Data Processing Pipeline
8.1 Workflow Design
___8.1.1 Defining Requirements and Setting Goals
___8.1.2 Workflow Step-by-Step Design
___8.1.3 Selecting a Technology Stack
___8.1.4 Workflow Monitoring and Improvement
8.2 Batch Processing
___8.2.1 Batch Processing Concepts and Features
___8.2.2 Introduction and Comparison of Batch Schedulers
___8.2.3 Design and Implement a Batch Workflow
___8.2.4 Batch Processing Optimization
8.3 Real-time processing
___8.3.1 Real-time processing concepts and features
___8.3.2 Introduction and Comparison of Streaming Platforms
___8.3.3 Designing and Building a Real-Time Data Pipeline
___8.3.4 Real-time processing optimization
8.4 Batch Processing vs. Real-Time Processing
___8.4.1 Key Differences Between Batch and Real-Time Processing
___8.4.2 Guide to Selecting a Processing Method Based on System Requirements
___8.4.3 Hybrid Architecture

[PART 03] System Architecture Design

▣ Chapter 9: Log Design and Operation
9.1 Log collection, storage, analysis, and visualization
___9.1.1 The Role of Logs
___9.1.2 Log Types
___9.1.3 Log Collection Methods and Tools
___9.1.4 Efficient Log Storage Strategies
9.2 Log Format and Management Strategy
___9.2.1 The Importance of Log Format Standardization
___9.2.2 Log format types and selection criteria
___9.2.3 Log Level Definition and Utilization
___9.2.4 Guidelines for Writing Log Messages
9.3 Elastic Stack
___9.3.1 What is the Elastic Stack?
___9.3.2 Elasticsearch
___9.3.3 Logstash
___9.3.4 Kibana
___9.3.5 Beats
9.4 A/B Testing and Experimental Design
___9.4.1 What is A/B testing?
___9.4.2 Principles of Experimental Design
___9.4.3 Statistical Significance Test and Results Interpretation
___9.4.4 Procedures and tools for conducting A/B testing

▣ Chapter 10: System Architecture
10.1 Considerations when Designing System Architecture
___10.1.1 Non-functional requirements analysis method
___10.1.2 Identifying and Managing Design Constraints
___10.1.3 Introduction to Architectural Patterns
10.2 Monolithic vs. Microservices
___10.2.1 Monolithic Architecture
___10.2.2 Microservices Architecture
___10.2.3 Comparative Analysis of Monolithic and Microservice Architectures
___10.2.4 Transition Strategy to Microservices
10.3 Distributed System Design Principles
___10.3.1 Understanding Distributed System Tradeoffs
___10.3.2 Considerations when Designing Distributed Systems
___10.3.3 Distributed System Fault Tolerance Design
10.4 Bottleneck Identification and Resolution Strategies
___10.4.1 Performance Bottleneck Identification Methodology
___10.4.2 Bottleneck Types
___10.4.3 System Performance Measurement and Analysis Tools
___10.4.4 Bottleneck Resolution Strategies

▣ Chapter 11: System Optimization and Scalability
11.1 Load Balancing
___11.1.1 The need for and types of load balancing
___11.1.2 Load Balancing Algorithm
___11.1.3 Considerations when introducing a load balancer
___11.1.4 Load Balancers in Cloud Environments
11.2 Caching
___11.2.1 Basic Principles and Effects of Caching
___11.2.2 Caching Strategy
___11.2.3 How to maintain cache data consistency
11.3 Container Orchestration
___11.3.1 Docker container concepts
___11.3.2 Building and Managing Container Images
___11.3.3 Container Orchestration with Kubernetes
___11.3.4 Introducing Cloud-Based Container Services
11.4 Auto Scaling
___11.4.1 Horizontal Scaling vs. Vertical Scaling
___11.4.2 Setting Auto Scaling Policies and Rules
___11.4.3 Considerations for Autoscaling
11.5 Performance Measurement and Analysis Methods
___11.5.1 Selecting Performance Metrics
___11.5.2 Using Performance Analysis Tools
___11.5.3 Bottleneck Identification and Improvement Strategies
___11.5.4 Building a Performance Test Environment and Designing Scenarios

▣ Chapter 12: Building a Large-Scale Language Model System
12.1 Selecting and Configuring Search Components
___12.1.1 Search-Based LLM Overview
___12.1.2 Comparison of Vector Search and Keyword Search
___12.1.3 Search Tool Comparison
___12.1.4 Search Performance Optimization and Scaling Strategies
12.2 Selecting and Configuring Generation Components
___12.2.1 Comparison of types and characteristics of generative models
___12.2.2 Comparison of major LLMs such as GPT, LLaMA, and Claude
___12.2.3 Criteria for selecting a generation model
___12.2.4 LLM Optimization Strategy
12.3 LLM System Architecture Configuration Strategy
___12.3.1 Comparison of Prompts, Contexts, and Fine-Tuning
___12.3.2 Single-Model vs. Multi-Model Combination Design
___12.3.3 API Design Principles for LLM-Based Applications
___12.3.4 Model Context Protocol (MCP)
___12.3.5 Efficiency Maximization Strategies for Cost Reduction
12.4 RAG System Architecture Configuration Strategy
___12.4.1 RAG System Overview
___12.4.2 RAG Architecture Construction Process
___12.4.3 RAG System Performance Evaluation and Improvement Strategies

[PART 04] Service Operation Guidelines

▣ Chapter 13: Security and Protection
13.1 AI Law and Regulation
___13.1.1 Overview of Key AI-Related Laws and Regulations
___13.1.2 Responsibility and Legal Risks of AI Systems
___13.1.3 Privacy Policy
___13.1.4 Operating Procedures for AI Compliance
13.2 Data Security Strategy
___13.2.1 Data Protection Principles and Security Model
___13.2.2 Data Encryption and Access Control
___13.2.3 Data Sharing and Transfer Methods
___13.2.4 Data Security Monitoring and Auditing
13.3 Data Security Incident Response and Recovery Process
___13.3.1 Data Breach Incident Types and Case Analysis
___13.3.2 Data Security Incident Response Framework
___13.3.3 Automated Breach Detection and Response
___13.3.4 Data Recovery and Recurrence Prevention Strategies
13.4 Privacy Policy
___13.4.1 Data anonymization and pseudonymization techniques
___13.4.2 Establishing a data collection and utilization policy
___13.4.3 Technical measures to protect personal information

▣ Chapter 14: Cost Management
14.1 Cloud Cost Optimization
___14.1.1 Cloud Service Cost Structure
___14.1.2 Strategies for Reducing Model Training Costs
___14.1.3 Long-term cost savings
___14.1.4 Cost Tracking and Notifications
14.2 Setting Service Level Agreements
___14.2.1 What is an SLA?
___14.2.2 SLA Design and Operation Plan
___14.2.3 Penalty and Compensation Policy for SLA Violation
14.3 Cost Management and Optimization Strategies
___14.3.1 Cost Data Collection and Integration
___14.3.2 Cloud Cost Analysis and Forecasting
___14.3.3 Optimizing Resources and Improving Utilization

▣ Chapter 15: Disaster Recovery and High Availability Design
15.1 Failure Scenarios and Recovery Strategies
___15.1.1 Identifying and Responding to Data Pipeline Failures
___15.1.2 Model Serving Interruption Recovery Process
___15.1.3 Batch Processing System Recovery Strategy
___15.1.4 Real-time processing system recovery strategy
___15.1.5 Fault Isolation in Distributed Computing Environments
15.2 Data Backup and Restore Strategies
___15.2.1 Large Dataset Backup Architecture
___15.2.2 Model Checkpoint Management and Restoration
___15.2.3 Optimizing Incremental and Full Backups
___15.2.4 Metadata and Feature Store Recovery Methods
15.3 High Availability Design Patterns
___15.3.1 Configuring a Multi-Cluster ML Infrastructure
___15.3.2 Ensuring Data Lake/Warehouse Availability
___15.3.3 Model Serving Layer Redundancy Design
___15.3.4 Fault Recovery Mechanism of Real-Time Analysis System

▣ Appendix A
A.1 RESTful API Practical Guide
A.2 Redis Practical Guide
A.3 RDBMS Practical Guide
A.4 OpenSearch Practical Guide
A.5 Elastic Stack Practical Guide
A.6 Grafana + Loki + Promtail/Agent Practical Guide
A.7 Docker Practical Guide
A.8 Kubernetes Practical Guide
A.9 Apache Kafka Practical Guide
A.10 Apache Flink Practical Guide
A.11 Apache Airflow Practical Guide
A.12 Apache Spark (PySpark) Practical Guide

▣ Appendix B
B.1 Real-time processing architecture
B.2 Batch Processing Architecture
B.3 RAG Architecture
B.4 Lambda Architecture
B.5 Data Lakehouse Architecture

▣ Appendix C
C.1 Characteristics of Data Science Projects
C.2 Project Phase Management Strategy
C.3 Applying Agile Methodologies
C.4 Outputs and Management Documentation
C.5_ Data Science Project Risk Management

★ What this book covers ★

◎ Core theories of data science, including data analysis, visualization, and exploratory analysis.
◎ Overview of machine learning and deep learning model design and introduction to major application areas
◎ Data engineering practices such as data collection, preprocessing, integration, and governance
◎ Data storage design, architecture patterns, and data pipeline construction
◎ Workflow design, batch processing, and real-time processing system design and comparison
◎ API design, model deployment, CI/CD, performance monitoring, and MLOps concepts
◎ Log architecture design, Elastic Stack, and experimental design (A/B testing) principles
◎ System design strategies such as microservices, distributed systems, bottleneck analysis, and improvement
◎ System optimization and operation technologies such as caching, load balancing, and autoscaling
◎ Case studies of the latest AI architecture, including LLM and RAG system configuration strategies
◎ Data Security, Privacy Protection, Disaster Response, Backup/Restore, and High Availability Design Guide
◎ Cloud cost optimization, SLA setting, and operational cost management strategies