|
| 1 | +<div align=center> |
| 2 | + <h1>FunRec Recommendation System</h1> |
| 3 | +</div> |
| 4 | +<div align="center"> |
| 5 | + |
| 6 | +English | [中文](./README.md) |
| 7 | + |
| 8 | +</div> |
| 9 | + |
| 10 | +This tutorial is a comprehensive guide to recommendation systems, primarily aimed at students with basic knowledge of machine learning who want to deepen their understanding of recommendation algorithms. The tutorial covers four perspectives: theoretical foundation, core algorithms, engineering practice, and interview preparation, providing a complete learning loop from theory to practice to job hunting. |
| 11 | + |
| 12 | +## 📚 Tutorial Content Overview |
| 13 | + |
| 14 | +### 🎯 **Recommendation System Overview** |
| 15 | +From the basic concepts of recommendation systems, this tutorial comprehensively introduces the significance, application scenarios, technical architecture, and related technical stacks of recommendation systems, helping beginners establish a comprehensive understanding and understanding of recommendation systems. |
| 16 | + |
| 17 | +### 🔍 **Retrieval Model** |
| 18 | +Explain the retrieval algorithms in recommendation systems, including: |
| 19 | +- **Collaborative Filtering**：Classic user collaborative filtering and item collaborative filtering algorithms |
| 20 | +- **Embedding-based Retrieval**：Retrieval methods based on embedding |
| 21 | +- **Sequential Retrieval**：Retrieval strategies considering user behavior sequences |
| 22 | + |
| 23 | +### 🎯 **Ranking Model** |
| 24 | +Systematically introduce the core technologies of ranking algorithms in recommendation systems: |
| 25 | + |
| 26 | +- **Memorization & Generalization**：Classic models such as Wide & Deep |
| 27 | +- **Feature Crossing**：Automated feature crossing methods |
| 28 | +- **Sequential Modeling**：User behavior sequence modeling techniques |
| 29 | +- **Multi-objective Modeling**：Multi-task learning in recommendation |
| 30 | +- **Multi-scenario Modeling**：Cross-domain recommendation and scenario adaptation |
| 31 | + |
| 32 | +### 🔄 **Re-ranking Model** |
| 33 | +Discuss the re-ranking techniques in recommendation systems: |
| 34 | +- **Greedy Re-ranking**：Simple and efficient re-ranking strategies |
| 35 | +- **Personalized Re-ranking**：Consider user-specific re-ranking methods |
| 36 | + |
| 37 | +### 🚀 **Challenges & Trends** |
| 38 | +Explore the latest trends and challenges in recommendation systems: |
| 39 | + |
| 40 | +- **Model Debiasing**：Solve the bias problems in recommendation systems |
| 41 | +- **Cold Start Problem**：Recommendation strategies for new users and new items |
| 42 | +- **Generative Recommendation**：Recommendation methods based on generative models |
| 43 | + |
| 44 | +### 💼 **Projects** |
| 45 | +Provide complete practical experience of recommendation systems through real competition cases: |
| 46 | +- Problem Understanding and Data Analysis |
| 47 | +- Baseline Construction and Optimization |
| 48 | +- Multi-retrieval Strategy Design |
| 49 | +- Feature Engineering and Ranking Model |
| 50 | + |
| 51 | +### 🎤 **Interview Preparation** |
| 52 | +Organize the core knowledge points in the interview for recommendation algorithm engineers: |
| 53 | +- Machine Learning Fundamentals |
| 54 | +- Core Algorithms of Recommendation Models |
| 55 | +- Latest Technologies Development Trends |
| 56 | +- Practical Applications in Business Scenarios |
| 57 | +- HR Interview Skills |
| 58 | + |
| 59 | +## 🎯 **Learning Objectives** |
| 60 | + |
| 61 | +Through this tutorial, you will be able to: |
| 62 | +- 🔧 **Master Core Algorithms**：Deeply understand the core principles of algorithms in each phase of recommendation systems |
| 63 | + |
| 64 | +- 💻 **Gain Practical Experience**：Obtain end-to-end recommendation system development experience through project practice |
| 65 | +- 📈 **Keep Up with the Latest Technologies**：Understand the latest trends and technologies in recommendation systems |
| 66 | +- 🎯 **Pass the Technical Interview**：Have the competitiveness for recommendation algorithm engineer positions |
| 67 | + |
| 68 | +We also establish a **FunRec learning community (WeChat group + knowledge planet)**, where the WeChat group is convenient for daily communication and discussion, and the knowledge planet is convenient for content retention. Some early recorded videos related to technology are also on Bilibili [All technical sharing content is on Bilibili](https://space.bilibili.com/431850986/channel/collectiondetail?sid=339597). Since the WeChat group's QR code is only valid for 7 days, just add the following WeChat Code, with remark: **Fun-Rec**, you will be added into a Fun-Rec discussion group. If you think the WeChat group is too noisy, it is recommended to add the knowledge planet directly! |
| 69 | + |
| 70 | +<div align=center> |
| 71 | +<img src="book/img/join_community.png" alt="image-20220408193745249" width="400px";" /> |
| 72 | +</div> |
| 73 | + |
| 74 | + |
| 75 | +## Thanks |
| 76 | +**Core Contributors** |
| 77 | + |
| 78 | +<table border="0"> |
| 79 | + <tbody> |
| 80 | + <tr align="center" > |
| 81 | + <td> |
| 82 | + <a href="https://github.com/ruyiluo"><img width="70" height="70" src="https://github.com/ruyiluo.png?s=40" alt="pic"></a><br> |
| 83 | + <a href="https://github.com/ruyiluo">Ruyi Luo</a> |
| 84 | + <p><br> MSc, Xidian University <br> Senior Recommendation Algorithm Engineer </p> |
| 85 | + </td> |
| 86 | + <td> |
| 87 | + <a href="https://github.com/bokang-ugent"><img width="70" height="70" src="https://github.com/bokang-ugent.png?s=40" alt="pic"></a><br> |
| 88 | + <a href="https://bokang.io">Bo Kang</a> |
| 89 | + <p><br> PhD, Ghent University <br> Co-founder of <a href="https://nobl.ai/">nobl.ai</a> </p> |
| 90 | + </td> |
| 91 | + </tr> |
| 92 | + </tbody> |
| 93 | +</table> |
| 94 | + |
| 95 | +Special thanks to [kenken-xr](https://github.com/kenken-xr)、[swallown1](https://github.com/swallown1)、[Lyons-T](https://github.com/Lyons-T)、[zhongqiangwu960812](https://github.com/zhongqiangwu960812)、[@wangych6](https://github.com/wangych6)、[@morningsky](https://github.com/morningsky)、[@hilbert-yaa](https://github.com/hilbert-yaa)、[@maxxbaba](https://github.com/maxxbaba)、[@pearfl](https://github.com/pearfl)、[@ChungKingExpress](https://github.com/ChungKingExpress)、[@storyandwine](https://github.com/storyandwine)、[@SYC1123](https://github.com/SYC1123)、[@luzixiao](https://github.com/luzixiao)、[@Evan-wyl](https://github.com/Evan-wyl)、[@Sm1les](https://github.com/Sm1les)、[@LSGOMYP](https://github.com/LSGOMYP) for their early help and support to this project. |
| 96 | + |
| 97 | + |
| 98 | +## Follow Us |
| 99 | +<div align=center> |
| 100 | +<p>Scan the QR code below to follow the Datawhale Official Account</p> |
| 101 | +<img src="book/img/datawhale_qrcode.jpg" width = "180" height = "180"> |
| 102 | +</div> |
| 103 | + |
| 104 | +Datawhale, a learning community focused on the field of AI. Our mission is for the learner, and grow together with learners. Currently, there are thousands of people have joined the learning community, and we have organized learning in various fields such as machine learning, deep learning, data analysis, data mining, web crawling, programming, statistics, MySQL, and data competitions. You can join us by searching for the Datawhale Official Account on WeChat. |
| 105 | + |
| 106 | + |
| 107 | +## LICENSE |
| 108 | +<a rel="license" href="http://creativecommons.org/licenses/by-nc-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://img.shields.io/badge/license-CC%20BY--NC--SA%204.0-lightgrey" /></a> |
| 109 | +This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-nc-sa/4.0/">Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0)</a>. |
0 commit comments