Evaluating Recommendation Algorithms - Offline and Online Approaches
Offered By: Open Data Science via YouTube
Course Description
Overview
Discover the inner workings of Delivery Hero's recommendation algorithms in this 23-minute video presentation by Manchit Madan. Explore how gradient boosting, NLP, and representation learning are utilized to create personalized suggestions for cart completion and product recommendations. Gain valuable insights into the process of offline and online evaluations for recommender systems, including the importance of A/B testing and strategic offline assessments. Learn how to balance user experience improvements with business metrics, and understand the key factors in selecting the most effective algorithms for various use cases. Delve into topics such as cross-selling recommendations, the necessity of offline evaluation, and the design of online A/B tests, equipping yourself with knowledge to make data-driven decisions in the realm of recommendation systems.
Syllabus
- Introductions
- About the Author
- Cross-selling Recommendations
- Why do we need offline evaluation?
- What is offline evaluation?
- How to Design Online Evaluation A/B Tests?
- Offline decide the best recommendation algorithm
- Conclusion
Taught by
Open Data Science
Related Courses
From Graph to Knowledge Graph – Algorithms and ApplicationsMicrosoft via edX Social Network Analysis
Indraprastha Institute of Information Technology Delhi via Swayam Stanford Seminar - Representation Learning for Autonomous Robots, Anima Anandkumar
Stanford University via YouTube Unsupervised Brain Models - How Does Deep Learning Inform Neuroscience?
Yannic Kilcher via YouTube Emerging Properties in Self-Supervised Vision Transformers - Facebook AI Research Explained
Yannic Kilcher via YouTube