Capstone did provide a true test of Data Analytics skills. Its like a being left alone in a jungle to survive for a month. Either you succumb to nature or come out alive with a smile and confidence.
Wow i finally managed to finish the specialization!! definitely learned a lot and also found out difficulties in building predictors by trying to balancing speed, accuracy and memory constraints!!!
By Michael S•
Of all the offerings in the specialization, this one felt like it was thrown together in less than hour. I expected to have to learn quite a bit of material on my own, but even the references to additional materials were very thin.
I could have saved many days if more guidance on the project workflow would have been given. The pre-processing of the data was quite extensive (9 steps before generating the ngram tables I used in my model) and was the key to getting decent results IMHO, but one had to step on a quite a few landmines to figure this out.
The problem was an interesting one and I ended up reworking it after passing with 95% (the only class in the specialization I didn't get 100% on) because I didn't have time to implement much of what I had to figure out by 'hard-knocks'
By Marco S C•
Unfortunately this project is not fully aligned with all the previous program, which is a shame. Ideally, the project was more related to quantitative data, or have compulsory module NPL. It was certainly a very important learning, but very stressful to have to grasp NPL and do the project in a short time.
Learning NPL in short time in a DIY way without any help it was very negative and stressful.
By Sandro R•
As other reviewers said, the Capstone is too unconnected to the rest of the specialization. In the end, there is no metric as to what makes your model successful, it's just the Slides and the appearance of the Shiny app that counts towards the total mark. Also, the topic (Natural Language Processing) is just too unconnected to anything seen in the other courses. It was fun, but felt a bit off.
By Tavin C•
The series leading up to the capstone was excellent but the capstone itself was a disappointment. Very little instruction was provided and the grading criteria were flawed. Also, most of what we learned in the first 9 courses about statistics and machine learning turned out to be irrelevant to the capstone project.
By Clara B•
The course has nearly nothing to do with the previous themes. I already have had enough knowledge, but as there is no support by the team it seems to be rather time consuming for others.
By WONG L C•
I hope it will involve statistics analysis in the capstone project. It is kind of bias to apply NLP knowledge and develop data product in the capstone project.
By Sevdalena L•
Not enough information on how to approach the final project. The project itself is very time consuming with lots of self learning and unclear specifications.
By Lee M S•
The capstone project doesn't fully utilise d knowledge from earlier modules such as Machine Learning, statistical analysis, regression models n etc.
No physical way to complete the class within one session. Little is learned, no instruction is given, just build a thing that sort of works.
By Dmitri P•
The course is outdated and abandoned by the teachers.
SwiftKey engineers are nowhere to be seen.
There is no guidance.
By Yohan A H•
Thanks for the guide but I did the hole course without instructions, there were new thing that could be tougth.
need more details
By Cristin K•
The amount of background knowledge you need in order to get through this course is astonishing compared to the amount of knowledge you gain from the other 9 courses in the specialization. The first two tasks are really easy. The third one (creating a model) is ridiculous. It's nothing like the models we built in the modeling course. The number of people who have given up at that point and dropped is absurdly high. I spent a month and a half trying to get enough background to get a working model up and running and eventually just decided it's not worth it for just a Coursera certificate. No offense, but this is more like a final project for a master's degree.
I understand that the idea is to push people to be able to deal with different kinds of data, but you give us all the tools we need for a specific kind of data and then drop a completely different kind of data from a completely different field, and NONE of the modeling techniques or even the stats actually apply to this new type of data.
By Joerg L•
I currently taking this capstone and I must unfortunately say that this is the most worst course in the whole specialization. Of course the topic NLP and word prediction is interesting, but the problem is, that this is a dead course. A couple of students in the forum strugeling with details, but there is NO Mentor, no Professor or other course staff and no SwiftKey engineer as announced in the Project Overview.
So everything you have to figure out completely by yourself and this takes a lot of more time than the 4-9 hours. And also why should you pay for a course where you learn anyway only ba your own.
Pick any intersting topic you would like to work on and invest the time in this instead of paying for this Capstone without any support form Coursera, JHU or SwiftKey.
By Ben T•
The course is really just a structure for the final project. Most learning and programming techniques for the capstone are self taught and require intense research and experimentation. This entire certificate is more or less in the same vein. Only attempt this if you are confident of your skills as a self directed learner. Overall I found most of the courses to be disappointing in the series though I did finish.
Class offers nothing more to the previous 9 courses. The curators of the course seem to have given up at this point, basically telling us to do something on our own (to be graded amongst ourselves).
By Stephen E•
A poor end to a poor Coursera specializations.
By Runhao Z•