Inflearn brand logo image
Inflearn brand logo image
NEW
AI Development

/

Deep Learning & Machine Learning

[Beginner/Introductory] Implementing Recommendation Systems Through Various Examples

🧩 Rather than complex formulas or theory-focused explanations, the goal is to learn the core concepts of recommendation systems by directly implementing programs. 🛠️ Across 12 diverse, practical examples, we incrementally built recommendation systems for real-world use, covering content-based, collaborative filtering, and deep learning methods.

74 students are taking this course

Machine Learning(ML)
Deep Learning(DL)
PyTorch
AI
LLM

What you will learn!

  • Non-personalized Recommendation Algorithm: Concept and Implementation

  • Personalized Recommendation Algorithms: Concepts and Implementation

  • Non-personalization, personalization algorithms, and diversity-aware recommendation systems: Working principles and implementation

Learn about these things

Master the step-by-step recommendation system from basic to advanced

  • Considering the learner's level of understanding, the lectures are structured to gradually advance from basic concepts .

  • It is designed to allow for step-by-step learning, starting with basic statistical concepts, moving on to application stages using machine learning, and then to advanced recommendation techniques based on deep learning.

Strengthening the practical application of recommendation systems

  • You can learn the core strategies of recommendation systems in a practical way, covering model learning from statistics to deep learning, as well as hybrid techniques and diversity recommendations.

  • It is structured to handle a variety of situations that are actually encountered in practice, such as avoiding user cold start problems or overly similar recommendations.

  • We have deeply covered the main issues of recommendation systems frequently encountered in practice, thereby enhancing the applicability and problem-solving capabilities in the field.

Check out the learning content

Statistics-based recommendations

  • EDA(Exploratory Data Analysis)

  • Recommendations based on views

  • Rating-based recommendations

Content-based recommendations

  • BoW-based recommendations

  • TF-IDF based recommendations

  • LLM based recommendations

Machine learning based recommendations

  • Recommendation based on KNN (K-Nearest Neighbors)

  • MF (Matrix Factorization) based recommendation

Deep learning based recommendations

  • LightGCN based recommendation

  • SASRec based recommendations

Recommended Evaluation Criteria

  • Rating Prediction Evaluation Criteria

  • Ranking Evaluation Criteria

  • Diversity Assessment Index

Hybrid Recommendation System

  • Troubleshooting Cold Start Problems

  • Multi Recommended Model

I recommend this to these people

Software Developer

It is actually utilized in various domains such as shopping malls, content platforms, and education services, and if developers and engineers can understand and implement it, it can greatly contribute to enhancing product competitiveness .

Data Scientist and Data Analyst

The ability to model and evaluate integrated analysis of log data, user feedback, and item information will greatly enhance your competitiveness as a data professional.

Marketing Manager

By suggesting the most suitable products or content for each individual customer based on user behavior data, you can increase conversion rates, reduce churn rates , and maximize marketing performance.

Things to note before taking the class

Practice environment

  • Install Chrome browser and create a Google account

  • A PC with internet access

Learning Materials

  • Jupyter notebook files for practice

Recommended for
these people!

Who is this course right for?

  • Anyone interested in the principles and implementation of recommendation systems

  • Those interested in directly implementing a recommendation system, rather than complex formulas or theory-focused explanations

  • Recommendation system learners utilizing 12 diverse, practical examples.

  • People who want to build a recommendation system that reflects diversity, not just a simple recommendation algorithm.

Need to know before starting?

  • Python, a language easy for beginners to understand and learn.

  • Pandas, a library for analyzing and processing data

  • Google Colab, cloud-based lab environment (GPU support)

Hello
This is

안녕하세요, 강의를 맡은 조경원입니다.
저는 중소기업부터 대기업까지 다양한 산업 환경에서 웹 개발, 인공지능(AI), 그리고 AWS 인프라 구축 등 폭넓은 실무 경험을 쌓아왔습니다.

이러한 경험을 바탕으로 2022년부터는 오프라인에서 AI 분야의 강의를 진행하며, 실무와 이론을 연결하는 교육을 이어오고 있습니다.

Curriculum

All

25 lectures ∙ (9hr 2min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

Not enough reviews.
Become the author of a review that helps everyone!

Similar courses

Explore other courses in the same field!