Introduction to Recommender Systems
 |
Description
Book Introduction
If you are considering introducing a recommendation system
The first book you should read!
Recommendation features such as ‘tailored videos,’ ‘follow recommendations,’ and ‘products viewed by other customers’ are included in various services around us.
Recommendation systems are essential for services that handle a large number of items, as it takes too much time to choose what you want from a large number of options.
This book is a must-read for readers or organizations looking to implement a recommendation system.
The authors, who are recommendation system developers, examined success and failure cases they experienced, focusing on how to combine and apply recommendation systems to which services.
Instead of delving into the details of the recommendation algorithm, we will focus on an overview of the algorithm and how to apply it in practice.
This book will help you develop the right recommendation system to further evolve your service.
The first book you should read!
Recommendation features such as ‘tailored videos,’ ‘follow recommendations,’ and ‘products viewed by other customers’ are included in various services around us.
Recommendation systems are essential for services that handle a large number of items, as it takes too much time to choose what you want from a large number of options.
This book is a must-read for readers or organizations looking to implement a recommendation system.
The authors, who are recommendation system developers, examined success and failure cases they experienced, focusing on how to combine and apply recommendation systems to which services.
Instead of delving into the details of the recommendation algorithm, we will focus on an overview of the algorithm and how to apply it in practice.
This book will help you develop the right recommendation system to further evolve your service.
- You can preview some of the book's contents.
Preview
index
CHAPTER 1 RECOMMENDATION SYSTEM
_1.1 Recommendation System
_1.2 History of Recommendation Systems
_1.3 Types of Recommendation Systems
_1.4 Search and Recommendation Systems
_1.5 Summary
CHAPTER 2: RECOMMENDATION SYSTEM PROJECT
_2.1 Three skills needed to develop a recommendation system
_2.2 How to proceed with the recommendation system project
_2.3 Summary
CHAPTER 3 UI/UX of the Recommendation System
_3.1 The Importance of UI/UX
_3.2 UI/UX examples suitable for the purpose of users using the service
_3.3 UI/UX cases that fit the service provider's purpose
_3.4 Related Topics
_3.5 Summary
CHAPTER 4: Overview of Recommendation Algorithms
_4.1 Recommendation Algorithm Classification
_4.2 Content-based filtering
_4.3 Collaborative Filtering
_4.4 Comparison of Content-Based Filtering and Collaborative Filtering
_4.5 Selecting a Recommendation Algorithm
_4.6 Characteristics of symbolic data
_4.7 Summary
CHAPTER 5: RECOMMENDATION ALGORITHM DETAILS
_5.1 Algorithm Comparison
_5.2 MovieLens dataset
_5.3 Random Recommendation
_5.4 Recommendations based on statistical information or specific rules
_5.5 Association Rules
_5.6 User-User Memory-Based Method Collaborative Filtering
_5.7 Regression Model
_5.8 Matrix Decomposition
_5.9 Recommendation System Applications to Natural Language Processing Methods
_5.10 Deep Learning
_5.11 Slot Machine Algorithm (Bandit Algorithm)
_5.12 Summary
CHAPTER 6 COMBINATION WITH REAL SYSTEMS
_6.1 System Overview
_6.2 Log Design
_6.3 Real System Example
_6.4 Summary
CHAPTER 7 Evaluating Recommender Systems
_7.1 Three Evaluation Methods
_7.2 Offline Evaluation
_7.3 Online Evaluation
_7.4 Evaluation through user studies
_7.5 Summary
CHAPTER 8 Developmental Topics
_8.1 International Conference
_8.2 Bias
_8.3 Mutual Recommendation System
_8.4 Uplift Modeling
_8.5 Characteristics and challenges by domain
_8.6 Summary
APPENDIX A Netflix Prize
_A.1 Netflix Founding
_A.2 Recommendation System Development
_A.3 Netflix Prize
_A.4 Netflix's recommendation system
_A.5 Summary
APPENDIX B User-to-user memory-based methods
_B.1 Recommendation Process (1): Finding Users with Similar Taste Tendencies to You
_B.2 Recommended Process (2): Calculating the Predicted Average Value
_B.3 Recommendation Process (3): Recommending to Users
_1.1 Recommendation System
_1.2 History of Recommendation Systems
_1.3 Types of Recommendation Systems
_1.4 Search and Recommendation Systems
_1.5 Summary
CHAPTER 2: RECOMMENDATION SYSTEM PROJECT
_2.1 Three skills needed to develop a recommendation system
_2.2 How to proceed with the recommendation system project
_2.3 Summary
CHAPTER 3 UI/UX of the Recommendation System
_3.1 The Importance of UI/UX
_3.2 UI/UX examples suitable for the purpose of users using the service
_3.3 UI/UX cases that fit the service provider's purpose
_3.4 Related Topics
_3.5 Summary
CHAPTER 4: Overview of Recommendation Algorithms
_4.1 Recommendation Algorithm Classification
_4.2 Content-based filtering
_4.3 Collaborative Filtering
_4.4 Comparison of Content-Based Filtering and Collaborative Filtering
_4.5 Selecting a Recommendation Algorithm
_4.6 Characteristics of symbolic data
_4.7 Summary
CHAPTER 5: RECOMMENDATION ALGORITHM DETAILS
_5.1 Algorithm Comparison
_5.2 MovieLens dataset
_5.3 Random Recommendation
_5.4 Recommendations based on statistical information or specific rules
_5.5 Association Rules
_5.6 User-User Memory-Based Method Collaborative Filtering
_5.7 Regression Model
_5.8 Matrix Decomposition
_5.9 Recommendation System Applications to Natural Language Processing Methods
_5.10 Deep Learning
_5.11 Slot Machine Algorithm (Bandit Algorithm)
_5.12 Summary
CHAPTER 6 COMBINATION WITH REAL SYSTEMS
_6.1 System Overview
_6.2 Log Design
_6.3 Real System Example
_6.4 Summary
CHAPTER 7 Evaluating Recommender Systems
_7.1 Three Evaluation Methods
_7.2 Offline Evaluation
_7.3 Online Evaluation
_7.4 Evaluation through user studies
_7.5 Summary
CHAPTER 8 Developmental Topics
_8.1 International Conference
_8.2 Bias
_8.3 Mutual Recommendation System
_8.4 Uplift Modeling
_8.5 Characteristics and challenges by domain
_8.6 Summary
APPENDIX A Netflix Prize
_A.1 Netflix Founding
_A.2 Recommendation System Development
_A.3 Netflix Prize
_A.4 Netflix's recommendation system
_A.5 Summary
APPENDIX B User-to-user memory-based methods
_B.1 Recommendation Process (1): Finding Users with Similar Taste Tendencies to You
_B.2 Recommended Process (2): Calculating the Predicted Average Value
_B.3 Recommendation Process (3): Recommending to Users
Detailed image
Publisher's Review
Learn the know-how of a professional recommendation system developer! A guide to introducing a recommendation algorithm that knows you better than you know yourself.
In fact, recommendation systems have been around for a long time.
A restaurant's recommended menu and a bookstore's ranking of popular books are also types of recommendation systems.
As the number of decisions we have to make in our daily lives increases and the variety of choices we have, the demand for recommendation systems is growing.
Recommendation algorithms have also advanced by leaps and bounds, moving beyond the standardized method of recommending popular items to provide personalized recommendations tailored to each individual's interests and preferences.
Showing users their preferred items quickly increases user satisfaction, leading to increased sales and membership.
However, when actually applying it to services, various problems are encountered.
These include how to best structure the project, which recommendation systems to combine, what data to use, how to best present recommendation results, and how to evaluate the recommendation systems online before deployment.
This book addresses precisely those concerns.
Recommender systems are no longer a “nice-to-have” feature, but a “must-have.”
Learn the introductory know-how from authors with experience building real-world recommendation systems.
This will help create a recommendation system that supports users' decision-making by selecting valuable items among various items.
Content structure
[Chapter 1 Recommendation System]
We will provide an overview and history of recommender systems with some examples.
We will also briefly look at the types of recommendation systems and explain their differences from search systems.
[Chapter 2 Recommendation System Project]
We describe the team members required to develop a recommendation system and how the project will proceed.
[Chapter 3: Recommendation System UI/UX]
Introducing the UI/UX of the recommendation system.
User experience design is important because how you present recommended items can increase clicks and purchases.
[Chapter 4: Overview of Recommendation Algorithms]
We explain representative recommendation algorithms, collaborative filtering and content-based recommendation.
And we introduce the average value data input to the recommendation algorithm by dividing it into implicit and explicit.
[Chapter 5: Recommendation Algorithm Details]
We will explain the popularity recommendation and matrix analysis algorithms separately, and also look at what to watch out for when combining them in real-world services.
We also introduce the code that applies each algorithm using a movie dataset called MovieLens.
[Chapter 6: Combination with Real Systems]
Using a news delivery recommendation system as an example, we explain how the system is structured when incorporating recommendation algorithms into real-world services.
We will look at the recommendation system architecture, including server configuration, batch processing structure, and log design.
[Chapter 7: Recommendation System Evaluation]
Describes various evaluation metrics for recommender systems.
In addition to simple metrics like prediction error, we also look at metrics that measure the diversity of recommended items and measures unexpectedness.
[Chapter 8 Developmental Topics]
We will look at the International Conference on Recommender Systems, bias removal, and causal inference, which were not previously covered.
Target audience
Developers and data scientists who want to analyze data and provide customized services to each customer.
Developers and planners who want to learn the basics of integrating recommendation systems into their work systems.
Product managers and planners who need to communicate with developers to develop recommendation systems
ㆍUI/UX designer responsible for the user experience of the recommended service
In fact, recommendation systems have been around for a long time.
A restaurant's recommended menu and a bookstore's ranking of popular books are also types of recommendation systems.
As the number of decisions we have to make in our daily lives increases and the variety of choices we have, the demand for recommendation systems is growing.
Recommendation algorithms have also advanced by leaps and bounds, moving beyond the standardized method of recommending popular items to provide personalized recommendations tailored to each individual's interests and preferences.
Showing users their preferred items quickly increases user satisfaction, leading to increased sales and membership.
However, when actually applying it to services, various problems are encountered.
These include how to best structure the project, which recommendation systems to combine, what data to use, how to best present recommendation results, and how to evaluate the recommendation systems online before deployment.
This book addresses precisely those concerns.
Recommender systems are no longer a “nice-to-have” feature, but a “must-have.”
Learn the introductory know-how from authors with experience building real-world recommendation systems.
This will help create a recommendation system that supports users' decision-making by selecting valuable items among various items.
Content structure
[Chapter 1 Recommendation System]
We will provide an overview and history of recommender systems with some examples.
We will also briefly look at the types of recommendation systems and explain their differences from search systems.
[Chapter 2 Recommendation System Project]
We describe the team members required to develop a recommendation system and how the project will proceed.
[Chapter 3: Recommendation System UI/UX]
Introducing the UI/UX of the recommendation system.
User experience design is important because how you present recommended items can increase clicks and purchases.
[Chapter 4: Overview of Recommendation Algorithms]
We explain representative recommendation algorithms, collaborative filtering and content-based recommendation.
And we introduce the average value data input to the recommendation algorithm by dividing it into implicit and explicit.
[Chapter 5: Recommendation Algorithm Details]
We will explain the popularity recommendation and matrix analysis algorithms separately, and also look at what to watch out for when combining them in real-world services.
We also introduce the code that applies each algorithm using a movie dataset called MovieLens.
[Chapter 6: Combination with Real Systems]
Using a news delivery recommendation system as an example, we explain how the system is structured when incorporating recommendation algorithms into real-world services.
We will look at the recommendation system architecture, including server configuration, batch processing structure, and log design.
[Chapter 7: Recommendation System Evaluation]
Describes various evaluation metrics for recommender systems.
In addition to simple metrics like prediction error, we also look at metrics that measure the diversity of recommended items and measures unexpectedness.
[Chapter 8 Developmental Topics]
We will look at the International Conference on Recommender Systems, bias removal, and causal inference, which were not previously covered.
Target audience
Developers and data scientists who want to analyze data and provide customized services to each customer.
Developers and planners who want to learn the basics of integrating recommendation systems into their work systems.
Product managers and planners who need to communicate with developers to develop recommendation systems
ㆍUI/UX designer responsible for the user experience of the recommended service
GOODS SPECIFICS
- Date of issue: May 8, 2023
- Page count, weight, size: 296 pages | 183*235*20mm
- ISBN13: 9791169210980
- ISBN10: 1169210988
You may also like
카테고리
korean
korean
![GQ KOREA Mark (Monthly): December [2025]](http://librairie.coreenne.fr/cdn/shop/files/8ef265dbbfbf186523ed75ba7319009d.jpg?v=1765340328&width=3840)
