This Specialization covers all the fundamental techniques in recommender systems, from non-personalized and project-association recommenders through content-based and collaborative techniques. Designed to serve both the data mining expert and the data literate marketing professional, the courses offer interactive, spreadsheet-based exercises to master different algorithms along with an honors track where learners can go into greater depth using the LensKit open source toolkit. A Capstone Project brings together the course material with a realistic recommender design and analysis project.
Introduction to Recommender Systems: Non-Personalized and Content-Based
This course, which is designed to serve as the first course in the Recommender Systems specialization, introduces the concept of recommender systems, reviews several examples in detail, and leads you through non-personalized recommendation using summary statistics and product associations, basic stereotype-based or demographic recommendations, and content-based filtering recommendations. After completing this course, you will be able to compute a variety of recommendations from datasets using basic spreadsheet tools, and if you complete the honors track you will also have programmed these recommendations using the open source LensKit recommender toolkit. In addition to detailed lectures and interactive exercises, this course features interviews with several leaders in research and practice on advanced topics and current directions in recommender systems.
Nearest Neighbor Collaborative Filtering
In this course, you will learn the fundamental techniques for making personalized recommendations through nearest-neighbor techniques. First you will learn user-user collaborative filtering, an algorithm that identifies other people with similar tastes to a target user and combines their ratings to make recommendations for that user. You will explore and implement variations of the user-user algorithm, and will explore the benefits and drawbacks of the general approach. Then you will learn the widely-practiced item-item collaborative filtering algorithm, which identifies global product associations from user ratings, but uses these product associations to provide personalized recommendations based on a user's own product ratings.
Recommender Systems: Evaluation and Metrics
In this course you will learn how to evaluate recommender systems. You will gain familiarity with several families of metrics, including ones to measure prediction accuracy, rank accuracy, decision-support, and other factors such as diversity, product coverage, and serendipity. You will learn how different metrics relate to different user goals and business goals. You will also learn how to rigorously conduct offline evaluations (i.e., how to prepare and sample data, and how to aggregate results). And you will learn about online (experimental) evaluation. At the completion of this course you will have the tools you need to compare different recommender system alternatives for a wide variety of uses.
Matrix Factorization and Advanced Techniques
In this course you will learn a variety of matrix factorization and hybrid machine learning techniques for recommender systems. Starting with basic matrix factorization, you will understand both the intuition and the practical details of building recommender systems based on reducing the dimensionality of the user-product preference space. Then you will learn about techniques that combine the strengths of different algorithms into powerful hybrid recommenders.
Recommender Systems Capstone
This capstone project course for the Recommender Systems Specialization brings together everything you've learned about recommender systems algorithms and evaluation into a comprehensive recommender analysis and design project. You will be given a case study to complete where you have to select and justify the design of a recommender system through analysis of recommender goals and algorithm performance. Learners in the honors track will focus on experimental evaluation of the algorithms against medium sized datasets. The standard track will include a mix of provided results and spreadsheet exploration. Both groups will produce a capstone report documenting the analysis, the selected solution, and the justification for that solution.
如果订阅，您可以获得 7 天免费试听，在此期间，您可以取消课程，无需支付任何罚金。在此之后，我们不会退款，但您可以随时取消订阅。请阅读我们完整的退款政策。
此课程是 100% 在线学习吗？是否需要现场参加课程？
Most learners should be able to complete the specialization in 20-26 weeks.
What background knowledge is necessary?
Basic statistics or college algebra, and an ability to work with spreadsheets. For the honors track, you should also be comfortable implementing software in Java.
Do I need to take the courses in a specific order?
While each component can be useful by itself, the courses do build on each other and should be taken in order.
What will I be able to do upon completing the Specialization?
You will understand and be able to apply the major families of recommender algorithms: non-personalized, product association, content-based, nearest-neighbor, and matrix factorization. You will know and be able to apply a variety of recommender metrics, and will be able to use this knowledge to match the correct recommender system to appplications.
What is the honors track?
The honors track is an optional track where learners add programming recommenders in the open source LensKit toolkit. You should be comfortable with basic data structures, algorithms, and Java to attempt the honors track.
How does this Specialization relate to the prior Recommender Systems courses?
This specialization is an extended and updated version of the two prior versions of Introduction to Recommender Systems that we've offered through Coursera. About 50% of the video and 80% of the assessment material are new, and there is an honors track with programming assignments (which existed in the first version of the course only, and have been re-done for this specialization). The Capstone is entirely new.