Chevron Left
Back to Nearest Neighbor Collaborative Filtering

Learner Reviews & Feedback for Nearest Neighbor Collaborative Filtering by University of Minnesota

4.3
stars
234 ratings
54 reviews

About the Course

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....

Top reviews

NS

Dec 12, 2019

i found this course very helpful and informative. it explains the theory while providing real-world examples on recommender systems. the assignment helps in clearing up any confusion with the material

SS

Mar 31, 2019

Thank you so very much to open my eye see more view of recommendation field not only algorithms but use case and many trouble-shooting in worldwide business, moreover interview with noble professor.

Filter by:

51 - 54 of 54 Reviews for Nearest Neighbor Collaborative Filtering

By Jose R

May 27, 2018

Not clear examples in my opinion, and there was same complain made from several user and I never saw a reply and nothing was changed

By Konstantinos P

Apr 10, 2017

Unfortunately, the content of the course is poor. Too many interviews and some of them are pointless.

By Chunyang S

Feb 24, 2017

The content is too basic, and both lectures are too boring.

By Alex B

Aug 26, 2019

This course is taught at a really low level. Exercises are in spreadsheets which are more or less useless for practicing scale data applications. Spreadsheets contain information that makes importation into numerical processing software such as Pandas in Python or dplyr in R needlessly difficult and assumes the user can't even apply the distance formula.

Videos contain useful information but require wading through a lot of garbage at a slow pace, not useful for practitioners.

Assignments are poorly worded and some terminology is used questionably or flexibly (see the word "normalization"). Some assignments are so poorly done that there is an ongoing debate on the forums as to whether the autograder is messed up or the assignment instructions are messed up.

The "honors" track programming assignments use some piece of software with questionable generalizability. If I ever see lens kit in my own data work environment I will come back an edit my review but I find it unlikely. Furthermore, Java is not commonly used for data science or machine learning purposes making these assignments inaccessible to many users. Personally, I write in Java but I didn't find it fulfilling to waste my time playing "fill in the blanks" or "guess the library function" which is overall uninstructive.

Quiz assignments show true indications of the poor level of instruction. Recitation of pieces of information buried in 30 minutes videos that can be condensed into 5 are some of the finest examples of bad teaching. Regurgitating information found in required readings shows no level of comprehension of course material and is a severe disservice to students.

I will hope for better general coverage of recommender systems in the future in another course. Ideally using something applicable like Python, Scala (Spark), or even R.