The course material should be provided to allow better absorption of the large amount of information presented. some of the topics needs to be discussed further with more examples and concept declaration especially the hypothesis testing section.

The videos seem to be outdated. The material is honestly not that engaging. For a beginners course this might be good. Different people have different tastes. The content itself is pretty good I'd say.

Non-working labs, a few incorrect sentences, some things are not explained well enough (At least I feel so), at least one duplicated video - it's not bad, but sloppy.

Too much focus on "feature engineering", which is high-school level math on the columns. Better if more focus on the statistical concepts and theoretical backgroud.

I liked the course content but I would like a more interactive approach that show us how to do hypothesis testing in python. The teacher just reads the courses.

I think, instructor went too fast in many cases. Some topics needs to be restructured with more real life examples and interpretations.

Exam questions are phrased very poorly in a lot of cases and often don't do a good job of assessing what was taught.

Quizzes are too easy and pretty insipid. The course isn't terrible, but it's not something to spend money on.

The instructor was not explanatory enough. I suggest that it should be more of teaching than lecturing.

I do like the course in generall. But some slides, are very text heavy, which i do not prefer.

Content is good but teaching can me more better.

So next time please hire a good teacher.

The videos are not well explanatory enough.

Items not properly explained

it is to long!!

jjefesf

good

good

One of the most significant drawbacks of the course was the instructor's reliance on slides as a reading tool rather than a teaching aid. The slides presented the information in a rather static and passive manner, which made it difficult for me , to engage with the material effectively. Instead of actively demonstrating the application of formulas and concepts, the instructor merely read the text on the screen, leaving us to decipher the practical aspects on our own.

This approach posed several challenges. First and foremost, it hindered our understanding of the material. Exploratory Data Analysis (EDA) is a hands-on process that requires practical application, and it's crucial to see how formulas and concepts are applied in real-world scenarios. Unfortunately, the course did not provide sufficient guidance in this regard.

Moreover, this teaching method made it challenging to maintain focus and engagement throughout the course. It's difficult to stay engaged when the instructor's presentation primarily consists of reading text from slides. It would have been much more effective if the instructor had actively demonstrated how to use the formulas and provided examples that allowed us to see EDA in action.

To enhance the course and improve the learning experience, I would strongly recommend that the instructor adopt a more interactive and practical approach. This could involve incorporating hands-on exercises, real-world case studies, or live demonstrations of EDA techniques. Providing opportunities for students to actively apply what they've learned would undoubtedly lead to a more engaging and effective learning experience.

This course is too surface. You must have a solid background in statistics and be familiar with pandas/numpy python libraries, otherwise you will spend a lot of time just to learn these libs. Also there is some basic info in lectures but assignments contain much complex and harder tasks which were not discussed in the lecture. And the tasks already have answers , so there are questions and solutions in one place, it is very weird and annoying

Note enough exercisese. In fact there really were almost no exercises, except in the Honors section (the optional 5th week - a peer reviewed project).

Lectures were too fast and not always clear. Ambiguous language was frequently used. I believe the instructor does know the subject, but there is too much glossing over. Going to look for a better class with more exercises and clearer definitions.

Frankly, the presenter is a poor educator and the course materials are weak. The examples are limited, some explanations verge on incorrect (description of p-values), and several of the graded test questions are ambiguous and encourage rote learning of the teacher's preference/positions, rather than testing the underlying concepts. I expect better from IBM.

Course videos are way too long.

No Jupyter support, so for the coding exercise one has to download the notebooks and either use Google Colab or locally installed Jupyter notebook.

The explanation from mentor in this course was not that great. It felt like he was just reading some lines from an script, rather than explaining in simple terms.

The course starts well. Then it goes to statistics and not so much to machine learning. The assignment is not so geared towards machine learning.

the lecture seemed difficult to follow. i wish things where better explained. had to go back and take some other courses to enable me catch up