Too basic and too easy

The journey was well

A little boring...

good start.

Very boring

Nice course

bit boring

This course was fairly disappointing. Apart from the actual steps of the methodology, it does not properly teach the concepts mentioned in the course. For instance, the ROC curve used in the case study: I actually understood how it works from the forum, because one of the admins was kind and has given a very professional and well explained answer. I wouldn't say this course is a waste of time, but I believe it addresses superficially most concepts. I am a firm believer in explaining only a couple of things and doing them very well. The labs are bridging some gaps, so extra points for that. The chosen case study is not thoroughly explained - it uses methods that we are not given any context for and only the very obvious elements are explained. The parts addressing the case study need a serious revision. If you are not following the Data Science Specialization, I would recommend you find a better course on Data Science Methodology - this course is not it.

On the plus side, I did like the final assignment: yes, it is theoretical, yet it helps you really revise all that you've learned in the course.

Several errors throughout the course. 1. Module 2 - default Jupyter cell output does not show Cuisine column mislabeling and inconsistency as is stated in the text. 2. Module 3 - This question is barely english. "For predictive models, a test data set, which is similar to but independent of the training set, is used to determine how well the model predicts outcomes—using a training or test. A test data set happens during which stage in Foundational Data Science Methodology?" 3. Module 3 - "Which of the following statements describes how data scientists refine the model after the initial deployment and feedback stages?" Apparently the correct answer is "By incorporating information about participation and possibly refining with detailed pharmaceutical data." Note that the question does not refer to the case study but asks generally about Data Science Methodology, but the answer talks about pharmaceutical data...

Concepts are well explained. Case study is instead confusing and requires additional knowledge and experience (i.e.modelling section).

Sometimes topics are repeated in different sections making it difficult to understand if a task should be completed in a phase or in the next one (i.e. training sets are repeated in both data preparation and modelling).

Lab is not so useful, because it consists in executing python code without a complete understanding.

This course is fundamental to understand the methodology for data science, however I had to look at the videos multiple times to get an overview and I still feel I'm not familiar with it.

Not a useful course overall. The basic premise is fine and logical, but this course did not do a good job differentiating between the different steps involved in the Data Science Methodology and the terminology chosen and used was not explained very clearly or consistently.

Very dry and wordy videos. Example cases used were not straightforward and did not help me understand the concepts that were being conveyed. Good concepts to learn, but this course could have done a much better job at explaining them.

Thank you for the labs they were great!

Now about everything else:

1. The quality of videos was awfull: the sound was noticeably lower than in previous courses of the specialization,

2. Slides almost irrelevant to text material read, lots of material in such quickly-paced lectures,

3. Lots of medical and mathematical/statistical terms (and other advanced English vocabulary) make this course hard to comprehend to students who rather not that fluent in English.

Too much theory from the methodology being read out in the videos!!! Needs to be anecdotal and explained practically. The case study taken in the videos also could be simpler. Some concepts like modeling etc that needed to be focused on get the same focus as anything else. There is mention of predictive and descriptive across videos. But this could have been much better sequenced.

But the Jupyter notebooks provided a lot more value than the course itself.

I don't feel like I am gaining any knowledge with the help of your course I am just completing it but I dont think after I have completed this course I can tell anybody that I have learnt anything I feel like use less. I cant use this technology anywhere. futhermore if someone asks me whats the use of this IBM watson I am blank i can just play with it thats it nothing else is it helping us somewhere no. what you have to say in this ?

Hard to understanding content in this section. Especially where the tutor give an example of case study. If you want to do some revision fro this course. Please explain it in more general because for people who didnt have Stastic or IT , is not easy to understand. And also for final assignemtn. Could you please make some example how to finish it ? because i dont know to serve the answer like what exactly you want

Content was excellent in providing a framework to understand the process. Unfortunately, the tools used were completely inadequate. None of them functioned, course "TA's" frequently said problem was fixed, but it wasn't. Eventually, I just gave up on the ungraded exercises, but that meant I didn't actually learn anything beyond what I could have gotten by reading a book.

It was great to learn about the methodology and the process that goes into building a model. However, the video lectures felt like something that was quickly thrown together without any passion; extremely boring with a monotone voice, uninteresting slides, and a core example that was boring and felt uninspired.

Can't download the transcript for studying. Only get subtitles. A lot of information to learn. Found questions on the tests that were not in the material (I went back through the videos after the tests and no mention of some of the questions). Hope the rest of the courses are more complete.

Sometimes methodology can get verbose and abstract, but this content was quite good. The outline of topics and methodologies could have been a little tighter.The English is not so good and there are lots of spelling and grammar errors. There are also bad links for things like images.

The videos contained what felt like a lot of information that would have been bettered digested as a written lesson. I believe the course would have been better if all the information in the videos was also available as a pdf, to really be able to look at the slides while reading.

Doesn't fit as one of the starting courses for the data science certificate series: touching on a lot of jargons that will only be covered later. Plus, without writing the code and performing the analysis one can benefit very limitedly from this course.

The narrator speaks like he is reading the text. Content and especially case study is not easy to understand and somehow the method for teaching makes it more difficult. When you are trying to have full screen, resolution of the pictures are poor.

The topic is very interesting, the examples though are not sufficient. It would be helpful to exntend the lesson with many examples, some simple and some complicated, in order to give better knowledge and understanding. It is not very engaging.

the content of this course is not well designed for the beginners, it actually requires a lot of knowledge in data science field in order to fully capture this lecture. however this course is supposed to be an introductory course (I think).

The material was not engaging. The quizzes had questions with answer choices that were longer than the actual question and were all correct answers except for the addition, subtraction of one word or in one case a single Roman numeral.