Feb 13, 2019
One of the best courses I have taken on Coursera. Choosing Java for the lab exercises makes them inaccessible for many data scientists. Consider providing a Python version.
Dec 08, 2017
Nice introduction to recommender systems for those who have never heard about it before. No complex mathematical formula (which can also be seen by some as a downside).
von Peter P•
Oct 04, 2016
Too theoretical. I hope other parts will have more details.
von Aleshin A•
May 18, 2018
It would be better to make practice on Python.
von Andre C•
Mar 30, 2020
von Chunyang S•
Feb 03, 2017
Generally I like the contents of this course. I particularly like that insights are provided in terms of what aspects to consider when designing a recommender system; pros and cons of different approaches. However I'm also extremely bored watching the videos because looking at the lectures reading the scripts (most of the time with very slow speed) is one of the quickest way to send people to sleep. I'd hope the lectures will improve their presenting skills.
Another comment is the honours track assignments should really be put into more thoughts. I passed them with 100% credit, but I didn't feel I gained a lot useful knowledge through this exercise. Generally it felt to me that the complexity of the implementation is much much more than needed in relation to the complexity of the problems. Eventually this assignment became grinding with Java's verbose, annoying syntax and unnecessary computations designed in lab instruction. For example, in the first programming assignment, why if the ModelProvider object already computed the entire map of ratings, and the map is directly needed in the Recommender object, the Model object only provide API to retrieve individual rating but not the entire map?! Isn't it a wasteful computation to reconstruct the rating map? So I doubt the structural design of the program is sensible, or the expected solution would actually be done in real applications. Also I think Java is just a really out-dated, bulky language to work with in this kind of task. It really makes the assignment experience awful.
von Chun-Huang L•
Apr 06, 2020
The pace is too slow. Lectures spend lots of time on examples, and all kinds of possible variables.
These make stories very long, and badly-structured. It may be better to introduce only one concept at any moment, and discuss the problem and the solution immediately after mentioning the concept. That will help students to focus on the point and get it right sooner. It's good to combine all these concepts together after we've known everything, but not at the very beginning.
Also the programming assignment is really bad. As a CS student, I spent almost 90% of time on realizing the architecture, tools and libraries. I don't think these third-party libraries are helpful here. The same tasks can be implemented by pure Java code even more efficiently (for coding). Most non-CS students will find it difficult to use, while CS students can learn only little from the assignment since the core ideas to implement are far too easy.
I can feel how much knowledge lectures expect us to get from this lecture, but it really needs a rebuilding. Maybe trying to put a self limitation on video length will be a good start. Expressing a brief idea in a short video, and allowing students to consume one video even with only a piece of time, should be one of the most appealing part in flip-classroom.
von Akash S C•
Jun 22, 2019
Good course for basic intro to recommender system. However, some basic problems - videos are too long and Java for programming assignment was a huge disappointment. i tried picking the lenskit assignment with java but decided to get rid of it and replicated the assignment in python instead. it was taking too much time to learn Java back which will never be used in regular work for data science. python or R should have been used for prog assignment. time to update the course.
von Maksym Z•
Jan 30, 2017
Some useful terminology if you want to ever communicate with someone who does recommender systems.
Very diluted content.
Mostly large text slides with the presenter talking in a monotone voice.
Programming exercises are done in Java and require deploying an IDE + an unused open source project developed by the authors. Hint to the authors: use Python, R or Octave like everyone does.
Some of the questionaries are ambiguous.
von Jon H•
Feb 14, 2019
The content of this course is solid. It's a good introduction to content based and non-personailzed recommender systems. However, the presentation is poor. The course is largely based around videos which appear to be single takes. Snappier, well edited videos would have been better and, as a result, I often found myself skimming the transcripts rather than watching the videos.
von Sachin S•
Oct 31, 2016
I expected a lot from this course but it could have been a lot better - lengthy videos, not trying to explain the concepts in an understandable ways. Ended up confusing with various interviews and what are differences between various content based recommenders. The programming exercises were good and provided a good overview.
von Sharat M•
Nov 09, 2016
As an introductory course, the content was good. But I wish the approach was more analytical and more hands on. Rather than history of Recommender systems & what happened in the 90s, I would have been happier if the course was able to throw light on the latest stuff in this field, the latest mathematical techniques etc.
von Faizan A•
Mar 01, 2017
The assignments are not very relevant to what is being taught. Java 7 instead of Java 8 makes things too verbose. Lenskit is painful to use and in the week 4 Honors assignment its just impossible to get the results desired by the grader. I would suggest the Teaching team to use R/python scikit instead of Java
von Paulo E d V•
Dec 08, 2016
Ok, it's an introduction, but it could at least show us some math or pseudocodes. A part from that, the course is really awesome. Well structured classes, good explanations and incredible interviews
von Joeri K•
Mar 23, 2019
It would be nice to have a hierarchical overview of the recommender systems. It's easy to get lost which is a subcategory of which. Thanks for the course!
von Siddhartha S B•
May 13, 2020
Honors track should be in Python. The subjective questions of the evaluation lacks clarity in some cases.
von Artur K•
Sep 12, 2017
The introduction is very slow in my opinion. Hopefully, it will pick up the pace in the later modules.
von Md. S R•
Jan 05, 2019
The lecturer were very lengthy, at least for me. I find it difficult to concentrate.
von Ruth B•
Aug 13, 2017
Not bad for an introduction, but I would have prefered it to be more technical
von Lucas P B•
Sep 04, 2019
Was expecting programming activities in Python or R, not in Java =/
von Michael B•
Dec 31, 2019
I feel like the course could've been condensed to 1 or 2 weeks max
von AISHWARY B•
Mar 29, 2020
Coding assignment should not be just restricted to java
Feb 27, 2020
수학개념이 부족해서 조금 추상적으로 이해하게 되었습니다.
von Oleg P•
May 24, 2020
There is no math in this course and it does not use Python. Therefore this course does a terrible job of preparing you for interview questions on Recommender systems. Personally I thought this course was a waste of my time and money. However the final excel exercise actually had some useful information, but it was only a 10 minute exercise after many hours of useless lectures. I could have done the same exercise for free.
von Alex B•
Aug 26, 2019
This course mostly works. Contains a lot of wasted video time where no information is communicated. Uses simplistic tools that don't scale to data applications or otherwise dated tools not really used by data scientists or machine learning engineers making exercises either simplistic or a waste of time. Better than other courses in the series in that the assignments are legible.
von Timea K•
Jul 02, 2017
You should talk about music recommender systems as well! It was just OK, but boring some times... You were talking about lots of evident things by Amazon, making the course question. if it is seriously a university content.