This course is for intermediate and advanced experts who want to actually implement recommendations. ^^ It's good because it contains content that is not easily seen.
5.0
ajaalsgus
100% enrolled
Thanks to this, my understanding of recommender systems has greatly improved. It's a really great lecture!
5.0
이지호
39% enrolled
I learned the concept of recommendation algorithms from information scattered on various blogs...ㅠㅠㅠㅠ It's nice to have it all organized in one place. I'm about to take a practical class, so I'll work hard!
What you will gain after the course
Concepts of recommendation algorithms
How various recommendation algorithms work
Implementing Recommendation Algorithms Using Python
Implementing a Personalized Recommendation System ✅ Rough but informative with Rough Coding!
The Secret to Successful Services: Recommendation System Algorithms 👨💻
Netflix, Amazon, YouTube, Spotify, and other world-renowned services, as well as services utilizing recommendation algorithms, are increasingly on the rise.
But... doesn't this sound like your story?
"Can I really grasp the concepts of recommendation algorithms correctly?" "I understand the concept of recommendation algorithms, but... how do I actually implement them?"
👇👇
Recommendation Systems 📌 With easy and intuitive Python!
As services utilizing recommendation algorithms continue to grow, the number of people wanting to learn about them is also steadily increasing. In line with this trend, <Personalized Recommendation Systems Using Python> aims to explain the accurate concepts and principles of recommendation algorithms using Python, an easy-to-understand and intuitive programming language.
Recommendation algorithms, why Python?
I hope this will be a meaningful time for those who want to learn about recommendation systems and those who wish to develop implementation skills suitable for practical work 😊
💻 Please check the prerequisite knowledge!
To take this course, a basic understanding of the Python language and the Numpy, Pandas, and Keras libraries is required.
Learn Differently, The World of Recommendation Systems 💌
Rough but truly informative! I am data analyst Rough Coding.
Hello! I am Geochin Coding, currently working as a Data Analyst at "one of the NAVER/Kakao/LINE companies".
Have you been wondering if you can truly grasp the concepts of recommendation algorithms? Do you feel like you understand it when reading a book, but feel completely lost when it comes to actually implementing the algorithm?
Through this course, I intend to solidly establish the foundation of recommendation algorithms by accurately explaining the concepts and operating principles. The course is structured not just to end with simple conceptual explanations, but to provide you with the confidence for actual implementation by coding the specific operating principles together.
Data Analyst, Rough Coding is 👨💻
Currently, I am performing data collection, processing, analysis, prediction, visualization, and task automation using Python and visualization tools (Tableau) at "one of the Naver, Kakao, or Line companies".
Key Experience
Bachelor of Arts in Statistics, Korea University (Graduated)
Korea University Graduate School, Department of Big Data Convergence (Enrolled)
QS World University Rankings Evaluator
Completed Advanced Artificial Intelligence Course at Korea University SW-Centered University
Korea University KUCC (Computer Club) Session Chair
Korea University Department Valedictorian (5 times), Overall Valedictorian (1 time)
Big Data Analysis Engineer Certification
Advanced Data Analytics Semi-Professional (ADsP) Certification
Efficient study methods for students dreaming of a career in data analysis
Consultation for junior analysts currently working in the field of data analysis
Those who are not in an IT role but want to apply IT technology to their own work
Through my knowledge, I hope this becomes a lecture that we create together.
The beginning is the most important part of everything. If you have any questions while learning, please inquire through [Q&A]. I am also conducting mentoring, so I hope to be of great help to those interested in data analysis. 😊
Unrivaled! Why this course is special 👍
A vague lecture focused only on simple conceptual explanations?
• The lecture doesn't seem much different from the materials scattered across the internet. • The conceptual explanations are good, but how exactly do I implement it in practice? • The difficulty level of the language itself is too high.
• This is a practical lecture focused on principles and hands-on practice, not just simple conceptual explanations. • It's not just a collection of web materials, but a compilation of authoritative reference books. • It utilizes Python for quick and easy learning.
1️⃣ A practical course focused on principles and practice, not just simple conceptual explanations
Simple conceptual explanations of recommendation algorithms are already scattered across many sites. However, no matter how good a conceptual explanation is, it is useless if it does not lead to an actual, accurate implementation.
In this course, we will not only provide a thorough explanation of recommendation algorithm concepts but also share solid know-how for implementing recommendation systems in real-world business environments.
2️⃣ Lectures using Python for easy and fast learning
The lectures are conducted using Python, a language that can be learned faster than other programming languages and is specialized for the field of artificial intelligence. The course is structured so that you can learn not only the understanding of recommendation algorithms but also the data engineering required for building AI models.
3️⃣ Accurate understanding through a systematic curriculum
This is not a lecture hastily put together by simply gathering random information scattered across various websites. The curriculum has been systematically structured based on organized content from authoritative reference materials.
Check out the learning content 📚
In this course 💻
It mainly covers the overall content of personalized recommendation technology.
Among them, we specifically cover personalized recommendation technology using continuous values.
It also explains Collaborative Filtering, Matrix Factorization, Deep Learning recommendation algorithms, and Hybrid recommendation systems that combine multiple recommendation algorithms.
Orientation
The purpose of this lecture is to understand the working principles of major personalized recommendation algorithms. The objectives and introduction of the lecture are summarized in a 5-minute orientation video, so please check it out via [Course Preview]!
Introduction to Recommendation Systems
We introduce the concept of recommendation systems, which select and present necessary information or products to users based on their past behavioral data or other information, along with various technologies and their evolutionary processes.
Main Recommendation Algorithms
Recommendation System Application Cases
Basic Recommendation Systems
This is the process of preparing and understanding the basic data for future theory and practice. We will introduce the basic operating principles of recommendation systems.
Reading Data
Popular Product Method
Measuring the Accuracy of Recommender Systems
Recommendations by User Group
Collaborative Filtering Recommendation System
We will introduce the concepts and operating principles of similarity-based Collaborative Filtering (CF) and enhance your understanding of these concepts by implementing them together.
Principles of Collaborative Filtering
Similarity Metrics
Basic CF Algorithm
Neighbor-based CF
Determining the optimal neighborhood size
CF considering user rating tendencies
Other methods for improving CF accuracy
User-based CF and Item-based CF
Performance Metrics for Recommender Systems
Matrix Factorization (MF) Based Recommendation
We introduce the concept and operating principles of Matrix Factorization (MF), which is based on matrix operations, and enhance your understanding of the concept by implementing it together.
Principles of the Matrix Factorization (MF) method
MF algorithm using SGD (Stochastic Gradient Descent)
Basic MF algorithm using SGD
MF algorithm with train/test split
Finding the optimal parameters for MF
MF and SVD
Using the Surprise Package
Learn the concepts and operating principles of a package that allows you to easily implement and test CF and MF-based recommendation systems.
Basic usage of Surprise
Algorithm Comparison
Specifying algorithm options
Comparison of various conditions
Using external data
Recommendation Systems Using Deep Learning
We will enhance our understanding of the concept by exploring the principles and practical applications of operating a recommendation system using artificial neural networks with multiple hidden layers.
Converting Matrix Factorization (MF) into a Neural Network
Implementing MF with Keras
Recommendation Systems Applying Deep Learning
Adding variables to deep learning models
Hybrid Recommender Systems
We will enhance understanding through methodological content on complementing and improving mutual performance by combining multiple recommendation algorithms, as well as through practical hands-on exercises.
Advantages of Hybrid Recommender Systems
Principles of Hybrid Recommender Systems
Hybrid Recommendation Systems (Combining CF and MF)
Using Sparse Matrix for processing large-scale data
By learning the methods for processing overwhelming amounts of data and the entire process of applying actual recommendation algorithms, you will gain a sense of practical, real-world skills.
The concept of Sparse Matrix and its use in Python
Applying Sparse Matrix to Recommendation Algorithms
Issues in building recommendation systems
Through a comprehensive summary of problems and issues that frequently occur when building an actual recommendation system, you will directly learn various know-hows that can help reduce trial and error during the actual production process.
New users and items (Cold Start Problem)
Scalability
Presentation of Recommendations (Presentation)
Use of Binary Data
Acquiring user's indirect evaluation data (Indirect Evaluation Data)
Check out the instructor's Q&A! 💬
Q. Is it mandatory to have prior knowledge of Python, Numpy, Pandas, and Keras?
You must know Python, but you don't need to study the other libraries too deeply in advance. I recommend looking up and studying only the parts you don't know as they come up while taking the course. The library functions used in the lectures are very useful and commonly used, so for those studying for the first time, they could serve as a guideline for what to study first. 😉
Q. Is the data provided in advance?
Of course. The data used in all lectures will be the MovieLens data, which was developed and verified by the GroupLens project at the University of Minnesota. You can download it via the data URL provided before the class begins.
Q. Can I develop an actual recommendation engine by taking this course?
In every lecture chapter, we cover not only the concepts of various recommendation algorithms but also practical hands-on exercises. Therefore, by making slight modifications to the code we practice together to fit your specific domain, you will be able to develop your own recommendation engine.
Q. Do I need to install Python separately or set up a development environment?
There is absolutely no need for that. To eliminate the hassle of installation and setting up a development environment, we will use Colab, a web-based editor provided by Google.
You can find detailed instructions on how to use Colab on my blog, or you can find more information by searching for "how to use Colab" on Google.
I am currently working at "one of the NAVER/Kakao companies"performing data collection, processing, analysis, prediction, visualization, and task automation using Python and visualization tools (Tableau).
⭐ Mentoring
Efficient study methods for students dreaming of a career in data analysis
Mentoring for junior analysts currently working in the field of data analysis
Those who are not in an IT role but wish to apply IT technology to their own work.
🌈 Mentoring Process
Conducted remotely via Zoom
Requirements: Computer, camera, earphones
Mentoring will proceed based on pre-prepared questions or your current situation.
🐯 Closing Remarks
The beginning is the most important part of everything. Let's make sure to achieve what you want with burning passion!
I learned the concept of recommendation algorithms from information scattered on various blogs...ㅠㅠㅠㅠ It's nice to have it all organized in one place. I'm about to take a practical class, so I'll work hard!
As you said, there are many blogs that cover the concept of recommendation algorithms, but there are many that are not continuous or lack information. I hope you can establish a clear concept through this opportunity~!
Fighting for practice too!!
-Rough Coding Dream-
This course is for intermediate and advanced experts who want to actually implement recommendations. ^^ It's good because it contains content that is not easily seen.
Thank you for leaving a good review.
As you said, I tried to make it not just a concept, but only practical content for actual implementation :)
This lecture is not the end, and I will come back with more interesting recommended topics.
Thank you.
-Rough Coding Dream-
Comments like this really give me a sense of accomplishment...ㅠ
Thanks to this lecture, I will return with a more unique recommendation algorithm lecture in the next lecture.
If you have the opportunity to introduce it to your company, I would really appreciate it if you could leave a review about it.
-Rough Coding Dream-
I'm so happy to hear that you've improved your understanding :)
Please continue to work hard for the remaining classes~!
If you have any questions, please leave them on the community Q&A board.
Thank you.
- Rough Coding Dream-
Everything is good, but I don't understand why they don't provide PDFs. They say that's for learning purposes..? I don't understand what they're talking about at all. The lectures are good. But isn't it obvious that they should share the PDFs that they use by default?? Or at least specify before payment that they won't share the PDFs; it really pisses me off.