It's very useful to be aware of separate steps in the activity of learning how to answer business questions with data. A concern, however, is that the contents of this course do not clearly distinguish between the steps. I appreciate that in real situations these steps are not distinct, but the purpose of the exercise is to conceptually distinguish them.

Excellent introduction to the data science process. The videos could have made use of a simpler example however, and there could have been more specific explanations about the kinds of models that data are used but the lab activities made things a bit clearer. The flow of the discussion was very clear though, so overall I'm very satisfied with the course.

My only suggestion will be to more clear on the lab session. Lectures , sometimes are hard to follow in lab or have difficulty to open files. Maybe , an update of lectures so we can follow lab easily. However, I learned on e important lesson, practice through lab , delete and try again it helps you to be familiar with the subject of the lecture.

I loved actually getting to see a practical example of how DS could be applied with the notebooks. It helps thinking on ways on how one could start their own practical projects in DS, and it increased my genuine interest in DS beyond just for job reasons. For sure it's more interesting than learning about tools I probably won't even use yet!

I will say since it is an online course and there is no physical lecturer present, plus there is no real time doubt clarifying options, the videos should be a bit slower, some times you are still thinking about a part and the next thing you realise is the video is near to its end.

rest i liked the content of the course its very good.

Much better / more useful than the prior two classes in the IBM Data Science track. The methodology described is a tad "big company" / slow-ish, but ok with it being used as a model for completeness, and am sure it will be of help to a lot of people, (who hopefully took notes to remember it! ;) ) for a long time to come.

Course really explains the Foundational approach clearly, The final project was really important to actually apply the methodology was were I learned the most. However, the case study showed in the modules was, sometimes, hard to understand due to technical vocaulary. A glosary would be good to have since the beggining

The information is useful and relevant. But the labs are limited in their utility, since the student isn't actually doing any of the work, just following along in the example. The lab information could just as easily be presented in the video, and vice versa. So it isn't really a "hands on" activity for practice.

This course is like a novel: too much words to explain a few concepts. I consider that you can compress a lot the length of the course. As a comparison I found here https://www.upgrad.com/blog/data-science-methodology/ an article called "Data Science Methodology: 10 Steps For Best Solutions". Straight to the point!

The final assignment was, in my opinion, too open ended and did not seem to be sufficiently conducive toward an in-depth application of the course material. A step-by-step walk.through project exercise on a pre-determined topic/scenario with specific questions at each stage, would have probably been more useful.

I think the course material was perfect. The final assessment could have been better, though. The way of giving answers and feedback can be improved. If you divide each phase of the project in a separate question, and enable peers to give feedback on each answer it would be better.

Thanks! Keep up the great work.

I enjoyed this course very much and appreciate the systematic way that the material was presented. The case studies were fantastic and I am taking away a structured methodology for completing data science projects. Special thanks to the professors for creating and teaching the course material. Well done!

1) Classes were OK but could be improved by sinchronizing/linking what is being said to what is written. Timing for viewing slides are poor. I had to watch nearly all videos twice to get all information I wanted.

2) The Labs were by a country mile the best part of the course. Keep this çgood job Folks.

The course describes the basic process used in data science work. It is very high level and as such does not really give you any specific skills, but I suppose that is not the purpose of it anyway and it does a nice job of explaining the basic data science methodology that can be generally applied.

The information and hands on projects in this course are great however the peer review process is lacking as it depends on another student to carefully review your submitted work. I've lost points on an assignment simply because my peer didn't carefully read both answers to a two step prompt.

The access to the data source from the Jupyter Notebook kept giving me a 403 Forbidden error so I was unable to see the results of the Python codes in the .ipynb files because the I don't think I had permissions or the link is/was outdated. Otherwise, very informative and exciting to learn.

Description of the overall methodology is good but individual stages could be more detailed. The distinction between some of the stages is not very clear, e.g., steps 3, 4, and 5. Individual videos for each step are very short. A lot is said very fast, but the slides are not very detailed.

It is refreshing to see a data science course that clearly talks about the methodology (which is fundamental to thinking about the process) rather than the technology (which, while useful, but the lure of technology is often used sloppily without real underlying thinking and reflection.).

the course was very particular about the hospital example i think it could have been more generalized or templated so that it could fit with other industries' understanding.

Rest was okay enough, although not very interactive since there is only presentation on screen and no instructor.

it s the est experience i ever hav that i have not learnt this much productive thngs on any onlne platform and its assigment and quiz its outstanding this helped me alot to understand it in deep sense i am very tjhankful to courser team that they hekping me to make my career bright.

Extremely powerful framework, good case study, mediocre analogical explanation. I am really impressed that IBM put heavy emphasis on the methodology before starting off with anything else. Having the mindset and the framework for execution is the most critical thing of any endeavor.

While the course was structured clearly explaining the purpose of each stage in the Data Science Methodology; however, the content in each stage could have been more detailed "in the presentations" and could have included more examples to explain 'what happens at each stage'.

a Great Understanding of How to see a real world problem and getting a proper path for that specific solution a instructor voice much feels like a radio jockey so recommended to add more easy example rather than hospital problem as it is not a field of interest for everyone

Good for those just getting into data science/analysis that don't know the full circle process beyond the number-crunching. For those that have produced full-scale deliverables, not entirely necessary, although you could get through it in a relatively short amount of time.

Really nice to have applied labs in a JupyterNotebook environment. The student can even replicate the codes (if wanted) in its own notebook.

Some improvement opportunity: add a lab in the 5th module. Also, the definition of training set vs. test set is a bit unclear, still