This book seeks to give readers with a preliminary but critical introduction and summary of e-commerce and big data analysis. This book introduces how to achieve data acquisition and pre-processing. Specifically, this book provides three representative and interesting scenarios to demonstrate the application of e-commerce and big data analysis, i.e., trajectory big data mining technology, e-commerce fraud and anti-fraud, and recommendation system. Also this book provides the basic and illustrative operation steps of Python programming language for e-commerce and big data analysis. By reading this book, readers can learn the basic concepts and principles of e-commerce and big data analysis.
Author(s): Jie Cao
Publisher: Springer
Year: 2023
Language: English
Pages: 368
Preface
I. Why Write a Book
II. Organization of the Book
III. Target Readers
IV. Study Suggestions
Acknowledgements
Contents
About the Author
1 Introduction
1.1 Overview of Business Big Data Mining and Applications
1.2 Big Data Infrastructure
1.2.1 Infrastructure Layer
1.2.2 Big Data Layer
1.3 Overview of Big Data Research in Commerce
1.3.1 Big Data Fusion
1.3.2 Knowledge Fusion
1.3.3 Trajectory Big Data Mining
1.3.4 Knowledge Graphs
1.3.5 User Portraits
1.3.6 E-Commerce Recommendation System
References
2 Data Collection in the Era of Big Data
2.1 Data Types of Business Big Data
2.1.1 Structured Data
2.1.2 Semi-structured Data
2.1.3 Unstructured Data
2.2 Online Business Big Data Collection Solution
2.2.1 Enterprise Data Collection
2.2.2 Web Crawler Data
2.2.3 Mobile Device Data
2.2.4 Database Data Collection
2.3 Offline Business Big Data Collection Solution
2.3.1 Physical Data Collection
2.3.2 Activity Data Collection
2.4 Cases of Business Big Data Collection
2.4.1 Precise User Portrait Description
2.4.2 Social Platform User Description
3 Pre-processing Big Data for Business
3.1 Business Big Data Pre-processing Techniques
3.1.1 Data Acquisition
3.1.2 Data Cleaning
3.1.3 Data Transformation
3.1.4 Data Integration
3.1.5 Data Imputation
3.2 Inconsistency Elimination Strategies for Multi-source Heterogeneous Commerce Big Data
3.3 Semantic Extraction and Analysis of Business Big Data
3.3.1 What Is Semantics
3.3.2 Semantic Analysis in Big Data
3.4 Business Big Data Pre-processing Case
4 Big Data Database for Business
4.1 Key-Value Store
4.1.1 Background to the Development of Key-Value Store
4.1.2 Key-Value Database Versus Relational Databases
4.1.3 Key Value Database Advantages
4.1.4 Redis
4.2 Column Family Store
4.2.1 Column Family Database Storage Structure
4.2.2 Column Family Database Features
4.2.3 HBase
4.3 Graph Store
4.3.1 The Concept of a Graph
4.3.2 Property Graph
4.3.3 Graph Database
4.3.4 Neo4j
5 Security Management on Big Data of Business
5.1 Traceability Technology of Business Big Data
5.1.1 The Definition of Data Traceability
5.1.2 The Definition of PROV
5.1.3 The Constraint of PROV Traceability Graph
5.2 Privacy Protection of Business Big Data
5.2.1 Data Desensitization Technology
5.2.2 Differential Privacy Protection
5.2.3 K-anonymity
5.3 The Data Sharing of Commercial Big Data
5.3.1 Access Control
5.3.2 Zero Trust Architecture
5.3.3 Attribute Based Encryption
5.3.4 Homomorphic Encryption
5.4 Blockchain Technology
5.4.1 Peer to Peer Network
5.4.2 Digital Signature
5.4.3 Hash Function
5.4.4 SPV Lightweight Verification and Melkel Hash Tree
5.4.5 Application of Blockchain in Business Big Data
5.5 Business Big Data Management Case
5.5.1 Demand Analysis
5.5.2 Network Architecture Design
5.5.3 Data Storage Design
6 Big Commerce Data Knowledge Representation
6.1 Multi-granularity E-Commerce Entity Construction Model
6.1.1 Multi-granularity E-Commerce Entity Category
6.1.2 E-Commerce Entity Recognition
6.2 Multi-category E-Commerce Entity Relationship Extraction
6.2.1 Multi-category E-Commerce Entity Relationship Categories
6.2.2 Multi-category E-Commerce Entity Relationship Extraction Methods
6.3 Multi-level Knowledge Representation Model
6.3.1 Knowledge Representation Model Based on Natural Language Processing
6.3.2 Knowledge Representation Model Based on Relational Network
6.4 Case Studies of Big Commerce Data Knowledge Representation
References
7 Business Big Data Knowledge Fusion
7.1 Semantic Extraction and Semantic Association
7.1.1 Subgraph Matching Algorithm for RDF
7.1.2 Knowledge Graph Keyword Search Algorithm
7.1.3 Semantic Association Ranking Techniques
7.2 User Profile Construction
7.2.1 User Data Collection
7.2.2 Segmentation of User Groups
7.2.3 Building a User Profile
7.2.4 Application of User Profiling
7.3 Knowledge Graph Construction
7.3.1 Knowledge Extraction
7.3.2 Knowledge Integration
7.3.3 Knowledge Storage and Graph Database Neo4j
7.4 Knowledge Reasoning and Interpretability
7.4.1 Knowledge Discovery and Reasoning
7.4.2 Rule-Based Knowledge Reasoning
7.4.3 Graph-Based Knowledge Reasoning
7.4.4 Neural Network-Based Knowledge Inference
7.4.5 Interpretability Analysis of Knowledge Reasoning
7.5 Business Big Data Knowledge Fusion Case
7.5.1 Introduction to Knowledge Fusion Tools
7.5.2 Technical Challenges of Knowledge Fusion
7.5.3 A Classic Case of Business Big Data Knowledge Fusion
8 Common Business Big Data Management and Decision Model
8.1 Robust Multi-task Learning for Clustering
8.1.1 Background
8.1.2 Problem Formalization
8.1.3 Cluster Multitasking Learning Based on Representative Tasks
8.2 Recommendations that Integrate User Interests
8.2.1 Background
8.2.2 Related to the Definition
8.2.3 Modeling Endogenous and Exogenous Interests of Users
8.2.4 Modeling Missing Data
8.2.5 A Recommendation Model that Incorporates User Interests
8.3 A Multi-objective Reinforcement Learning Framework for Community Deception
8.3.1 Introduction to Community Hiding Algorithms
8.3.2 Community Hiding Based on Multi-objective Reinforcement Learning
8.4 Mining of Periodic Coactive Populations in Trajectory Data
8.4.1 Background
8.4.2 Problem Formalization
8.4.3 Mining Algorithm for Periodic Populations in Trajectory Data
8.5 A Purchase Prediction Method Based on Semi-supervised Multi-view Learning
8.5.1 Feature Construction of co-EM-LR Model
8.5.2 Online Travel Customer Segmentation
8.5.3 Analysis of Online Travel Purchasing Patterns
8.5.4 Structure of the co-EM-LR Model
8.6 Recommendation Based on Probabilistic Matrix Decomposition and Feature Fusion
8.6.1 Application Scenarios of the PMF-MAI Model
8.6.2 Feature Construction of PMF-MAI Model
8.6.3 Structure of the PMF-MAI Model
8.7 Indoor Positioning Technology Based on Asynchronous Sensor
8.7.1 Indoor Positioning Technology Background
8.7.2 Asynchronous Sensing Method
8.7.3 Indoor Area Location Method for Asynchronous Sensing Data
8.8 Graph K-means Algorithm Based on Leader Recognition, Dynamic Game and Viewpoint Evolution
8.8.1 Study Scenarios, Motivations, and Meanings
8.8.2 Basic Knowledge and Problem Definition
8.8.3 Specific Framework
8.8.4 Experiment
8.8.5 Conclusion
9 Application of Business Big Data Management and Decision Making
9.1 Malicious User Fraud Detection
9.1.1 Malicious User Comment Detection
9.1.2 Recommended System Support Attack Detection
9.1.3 Credit Card Fraud Detection
9.2 Online Purchase Decision Model
9.2.1 Purchase Prediction Model
9.2.2 Personalized Recommendation Model
9.2.3 Sales Forecasting Model
9.3 Related Applications of Tourism E-Commerce
9.3.1 Point of Interest POI and Travel Package Recommendation
9.3.2 Travel Itinerary Planning
9.4 Business Applications of Location-Based Services
9.4.1 APP Takeaway Food
9.4.2 Car-Hailing Route Planning
9.4.3 Restaurant, Hotel and Gas Station Recommendation Based on Location Service
References
