VIETNAM NATIONAL UNIVERSITY HO CHI MINH CITY HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY VO THI KIM NGUYET ECOMMERCE GRAPH-BASED RECOMMENDATION SYSTEM Major: COMPUTER SCIENCE Major code: 8480101 MASTER’S THESIS HO CHI MINH CITY, July 2023 THIS THESIS IS COMPLETED AT HO CHI MINH UNIVERSITY OF TECHNOLOGY – VNU-HCM Supervisor: Le Thanh Van, Ph. Huynh Tuong Nguyen, Ph.D Examiner 2: Ton Long Phuoc, Ph.D This master’s thesis is defended at Ho Chi Minh City University of Technology (HCMUT) – VNU-HCM on 11th July 2023 Master’s Thesis Committee: 1. Tran Ngoc Thinh, Ph. Huynh Tuong Nguyen, Ph.
Ton Long Phuoc, Ph. Le Thanh Van, Ph. Nguyen Tien Thinh, Ph.D Secretary Approval of the Chairman of the Master’s Thesis Committee and Dean of Faculty of Computer Science and Engineering after the thesis being corrected (If any). CHAIRMAN OF THESIS COMMITTEE DEAN OF FACULTY OF COMPUTER SCIENCE AND ENGINEERING i VIETNAM NATIONAL UNIVERSITY - HO CHI MINH CITY SOCIALIST REPUBLIC OF VIETNAM HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY Independence – Freedom - Happiness THE TASK SHEET OF MASTER’S THESIS Full name: Vo Thi Kim Nguyet Student code: 2270346 Date of birth: Oct 10th 1995 Place of birth: Ho Chi Minh City Major: Computer Science Major code: 8480101 I.
THESIS TITLE: E-commerce graph-based recommendation system (Hệ thống gợi ý dựa trên phương pháp đồ thị trong thương mại điện tử) II. TASKS AND CONTENTS: 1. Introduction: • Introduce the research topic and its significance. • Provide an overview of the structure of the thesis.
Literature Review: • Conduct a comprehensive review of existing product recommendation techniques. • Analyze strengths and weaknesses of different approaches. • Identify gaps in the literature that the research aims to address. Problem Statement: • Clearly state the problem being addressed in the research.
• Highlight the need for improved recommendation approaches in the context of e-commerce. Methodology: • Design the research approach for developing and evaluating the recommendation system. • Define the criteria and metrics for evaluating the effectiveness of the system. Graph-Based Recommendation System Implementation: • Develop the recommendation system using graph embedding techniques.
• Implement graph construction methods based on user behavior data. • Incorporate Node2Vec and FAISS for graph embedding and indexing. Experimental Evaluation: • Conduct experiments to evaluate the performance of the developed system. • Compare the results with other existing recommendation models.
• Collect and analyze data on key evaluation metrics. Discussion of Findings: • Analyze and interpret the results of the experimental evaluation. • Discuss the implications of the findings in relation to the research objectives. Conclusion: • Summarize the key findings and contributions of the research.
• Discuss the practical implications of the research outcomes. Future Research Directions: • Suggest avenues for further research and improvements in the recommendation system. • Highlight areas where the proposed approach could be extended or refined. References: • List all the sources and references cited throughout the thesis.
Appendices: • Include any supplementary material, code snippets, graphs, or diagrams that enhance understanding. THESIS START DAY: Feb-06-2023 IV. THESIS COMPLETION DAY: Jun-09-2023 V. SUPERVISOR: Le Thanh Van, Ph.D Ho Chi Minh City, Jun-09-2023 SUPERVISOR CHAIR OF PROGRAM COMMITTEE (Full name and signature) (Full name and signature) DEAN OF FACULTY OF COMPUTER SCIENCE AND ENGINEERING (Full name and signature) Note: Student must pin this task sheet as the first page of the Master’s Thesis booklet iii ACKNOWLEDGEMENT This thesis marks the culmination of my research journey into graph-based modeling and its applications in data analysis and machine learning.
Graphs offer a unique perspective to understand complex relationships within vast datasets. Throughout this work, I explore fundamental concepts of graph-based modeling, delve into graph embedding techniques, and evaluate their efficacy in solving real- world problems. I extend my gratitude to my advisors, mentors, colleagues, and family for their unwavering support and encouragement. My hope is that this thesis inspires further research and innovative applications of graph-based models in various domains.
Thank you for joining me on this journey. Sincerely, Nguyet Vo Ho Chi Minh City, June 2023 iv ABSTRACT This thesis presents a graph-based recommendation system tailored for personalized content suggestions in ecommerce. Utilizing graph embedding methods such as DeepWalk and Node2Vec as part of Random Walks technique, the system captures users’ behavioural sequences and generates embeddings for items. These embeddings facilitate pairwise similarity calculations among items, forming the basis for content recommendations rooted in similarity metrics.
To tackle challenges like sparsity and cold start, additional information is seamlessly integrated into the graph embedding framework. Empirical evaluation using clickstream data demonstrates the superiority of the proposed approach over traditional collaborative filtering techniques in terms of both accuracy and efficiency. The study contributes a novel graph-based recommendation system addressing scalability, sparsity, and cold start issues, further enriched by the incorporation of supplementary data to enhance recommendation system efficacy. The results suggest that graph-based techniques hold potential for enhancing personalized recommendation systems across diverse domains, including ecommerce.
v TÓM TẮT LUẬN VĂN THẠC SĨ Luận văn đề xuất một hệ thống gợi ý dựa trên đồ thị cho việc cá nhân hóa gợi ý nội dung trong thương mại điện tử. Dự án sử dụng các kỹ thuật đồ thị như DeepWalk và Node2Vec của kỹ thuật Random Walks để nắm bắt chuỗi hành vi của người dùng và đề xuất các danh sách sản phẩm phù hợp. Những kỹ thuật này giúp tính toán độ xác suất giữa các cặp/ danh sách sản phẩm, từ đó tạo nền tảng cho gợi ý cho người dùng dựa trên hành vi của họ. Để giải quyết các thách thức như người dùng/ sản phẩm mới và khả năng mở rộng hoặc sự thưa thớt, thuật toán sẽ được bổ sung và tích hợp hệ thống nhằm đưa ra những gợi ý thông minh, phù hợp với sở thích của từng khách hàng.
Đánh giá thực nghiệm bằng dữ liệu lớn của hành vi khách hàng cho thấy phương pháp đề xuất vượt trội so với các phương pháp lọc cộng tác truyền thống về cả độ chính xác và hiệu suất. Nghiên cứu đóng góp một hệ thống gợi ý dựa trên đồ thị nhằm giúp khách hàng nhanh chóng định vị được những sản phẩm họ quan tâm để từ đó đưa ra quyết định đúng đắn khi mua sắm online cũng như khả năng cải thiện hiệu suất của hệ thống gợi ý cá nhân hoá. vi DECLARATION OF AUTHORSHIP I hereby declare that this thesis was carried out by myself under the guidance and supervision of Le Thanh Van, Ph.D; and that the work contained and the results in it are true by author and have not violated research ethics. The data and figures presented in this thesis are for analysis, comments, and evaluations from various resources by my own work and have been duly acknowledged in the reference part.
In addition, other comments, reviews and data used by other authors, and organizations have been acknowledged, and explicitly cited. I will take full responsibility for any fraud detected in my thesis. Ho Chi Minh City University of Technology (HCMUT) – VNU-HCM is unrelated to any copyright infringement caused on my work (if any). Ho Chi Minh City, June 2023 Author Vo Thi Kim Nguyet vii TABLE OF CONTENTS LIST OF FIGURES.
ix LIST OF TABLES. xi CHAPTER 1: INTRODUCTION. Background on recommendation systems and the importance of personalization. Scope of the research.
Novelty of the topic. 7 CHAPTER 2: OVERVIEW OF RECOMMENDATION SYSTEM. Recommendation System methods. Overview of existing literature on graph-based recommendation systems 16 2.
Graph-based learning Approaches for Recommender System (RS). Research results in application of Graph-based learning in Recommender System. Comparison of different graph-based algorithms. The advantages of using UMAP and FAISS in combination with Deep Walk and Node2Vec.
Session-based Recommendation System. Data collection and its characteristics. Data cleaning and preparation. Explanation of how the data was transformed into a graph-based representation.
Random Walks algorithm. Visualization with UMAP. Embedding Vector Search with FAISS. Evaluation of the Recommendation System.
67 CHAPTER 4: EXPERIMENTAL RESULTS. All Machine Learning (ML) Models. Traditional Recommendation Techniques. Sequence Models for Session-Level Data .86 CHAPTER 5: DISCUSSION AND CONCLUSION.102 ix LIST OF FIGURES Figure 1.
Example of PDP views in a session. Taxonomy of Recommendation System. The demonstration of graph learning based recommender systems. BFS and DFS search strategies from node 𝑢(𝑘 = 3).
Illustration of the random walk procedure in node2vec. The walk just transitioned from 𝑡 to 𝑣 and is now evaluating its next step out of node 𝑣. Edge labels indicate search biases 𝛼. Overview of graph embedding in Taobao: (a) Users’ behavior sequences: One session for user 𝑢1, two sessions for user 𝑢2 and 𝑢3; these sequences are used to construct the item graph; (b) The weighted directed item graph 𝒢 = (𝒱, ℰ); (c) The sequences generated by random walk in the item graph; (d) Embedding with Skip-Gram.
Attributes of raw dataset. Daily Visits summary. Flow of a user in a session. Example for view of all products of a user in a session.
Directed Graph with Weight. Undirected Graph with Weight. Middle and Remaining proportion. Final results of embedding vectors.
Node2Vec Embeddings Visualization. New dataset is generated from embedding vectors. Category-code in level 1 visualization. Cosine Similarity and L2 scores.
An imbalance in user interactions. List of results for a specific user. Correlation among categories. Each chunk in Association Rules algorithm.
Result in Association Rule algorithm. Traditional Recomendation System Models Results. Model and Result in NARM model. Co-occurrence matrix of items based on adjacency of items in same session.
Item & User Similarity matrix. Heterogenous Global Graph. Model Training and Evaluation. Results in HG-GNN model.92 xi LIST OF TABLES Table 2.
Comparison of different graph-based algorithms. Top-N Metrics Result. Comparison among dimensional reduction techniques. Comparisons among ML models and Graph-based approach.
Comparisons among traditional and graph-based models. Comparison among metrics in HG-GNN model. Comparison between Sequence Models and Graph-based model .94 1 CHAPTER 1: INTRODUCTION This chapter aims to enhance personalized recommendation systems in ecommerce by exploring advanced algorithms and conducting A/B testing for real- world insights. Using a large-scale dataset, we propose a state-of-the-art algorithm to improve accuracy and efficiency.
Our goal is to bridge theory and practice, revolutionizing recommender systems and maximizing user satisfaction in ecommerce. Leveraging a large-scale dataset from REES46 [1], we aim to revolutionize recommender systems, maximizing user satisfaction and platform diversity. Background on recommendation systems and the importance of personalization This thesis focuses on recommender systems in ecommerce, where personalized content recommendation is crucial due to the vast number of products available on numerous websites. Traditional recommender systems like Content-Based Filtering and Collaborative Filtering encounter issues with scalability, sparsity, and cold start problems, reducing their effectiveness in handling large-scale and sparse transaction records.
To address these challenges, the project proposes the use of graph embedding techniques, specifically Random Walks, to capture users’ behavioral sequences and generate item embeddings. These embeddings can then be utilized to recommend products to users, group similar products, and classify transactions based on meta-information about clusters, items, and users’ transaction use cases. The approach also employs Facebook AI Similarity Search (FAISS) for generating recommendations through embedding vector search. By leveraging graph-based learning, this thesis offers insights into enhancing recommender systems in ecommerce platforms while tackling the limitations faced by traditional methods.
Research Questions This thesis aims to address the effectiveness of graph-based techniques, namely Random Walks, and FAISS, in capturing users’ behaviour sequences and 2 generating item embeddings for improved product recommendations in ecommerce, compared to traditional methods. To investigate these research questions thoroughly, the following methodology will be employed: a.
