The topics covered in this course are really interesting. I learned a great deal by studying various papers covered in this course - Thank you to both instructors!
Very nice course sharing many types of knowledges around data / cleaning / type of data / several algorithms / organised Python coding
by Semant J P•
First about me - I been deeply involved in data science, and machine learning and trade on the financial markets. So, in addition to solid academic credentials, I have a real life practical experience. I took this course to check if there were some additional skills I could learn.
I was sorely disappointed. This is a completely useless course.
The first two courses in this specialization were amazing. This has been the worst organized and least practical course. As other reviews have pointed out, academic research on regime filtering was pandered out as machine learning in finance. I was expecting to learn practical instances of using supervised, unsupervised, deep learning used in finance. There was nothing of this sort.
I have never seen Q-Q plots being used in investment/hedge funds - we talk about annualized returns, standard deviation, Sharpe ratio, and drawdowns. These statistical markers were used by Vijay in the first two courses. Not here.
This course needs to be rebuild from scratch - and Vijay needs to be brought back in for real practical application of ML in financial services.
by Soheil S•
It was a terrible experience taking this course. Despite the two first courses, this one is disappointing! the ML instructor does not offer any useful material and all of the ML lectures contain ambiguous and useless material. The worst part is the quizzes. the multiple choices include ambiguous answers and that you should choose more than one and the ridiculous part is that either you would get the full mark or nothing! even if you choose some choices correctly and you never know what was your mistakenly chosen choice! I've tried the week 2 quiz for 9 times and have not been yet successful to pass it.
It's overwhelmingly complicated and unclear.
I didn't expect such a terrible course from EDHEC Business School and Coursera!
by Keith W•
The jump in Python programming was not handled well - it was far too complex and an order of magnitude more complex than anything that had come before. I enjoyed the theory, but feel lost with the Python component. A 12 minute lab session with a Princeton grad student was not nearly enough to grasp the material. Bring back Vijay who is excellent in teaching Python!
by M. W•
Interesting thema but bad cunstruction!
As I was enrolling in this course, I was excited to thinking about I can solve financial problems with ML on my own. But I must say I am totally disapointed after I finished it.
This is really berrible copparing to the first two courses from this specialization. The Master Vijad was so inspireble, he should come back and explian us how the Leb-Sessions was build and how can we use the programms, specially the Leb-Session for "Clustering and Grafical analysis for diversification" should be add on.
The PHD students were just reading what was happening on the slids from Prof. and even so, they read it wrong several times.
Acctually, this course can split to more than five weeks and evey details should explained specifically like the first two courses in this specialization. Maybe the Prof. Mulvey shold also find out this construction was kind of tight for someone who come from whith data-analyst or data-scientist background.
If the Master Vijad come again, I would think about to take this course one more time!
by Serg D•
Well, that was disappointing. What was the point bringing Princeton into this? Looks like edhec does not have in house ml experience. I did not find this course, exercises and labs to be practical at all. As another commentator said bring back Vijay!
by Dirk W•
Honestly, for this course, in the present state of work in progress, I can't give more than 1 star. Not well-constructed course, no right balance between theory and lab sessions. Theory on Machine Learning is on basic high-level concepts. Even the visual format of the lecture videos is irritating. Lab sessions are not always present, or not explained in a detailed manner, which is really a problem.
Stars are also missing because of a few frustrating quizzes and because of the lack of (quick/relevant) responses or answers of the moderators in the forum.
Please rework this course, with the high-quality other courses of this specialisation as example; please also take also the remarks of the students in the forum into consideration.
by Francisco C•
I learned about how can be used the machine learning in asset management, but to much theory and nothing practical. We received the lab done, and could not understand how implement. I missed the lab of the first two courses.
by Antony J•
I thought this was an excellent course that covers a wide range of applications of machine learning methods to investment management that have been published in top peer-reviewed finance and statistics / operational research journals. There is enough material in the excellent Python labs to lay the foundation for at least 6 months' worth of further research study.
A cautionary note: this is fast-paced and will most benefit learners who already have a foundation in machine learning from, for example, Andrew Ng's famous course. I also recommend first completing the preceding two courses in the specialization. This could be a tough course to take in isolation.
by Ziheng C•
Personally, this is the BEST online course I have ever seen. For students with basic knowledge in machine learning and finance, this can help them improve a lot, especially helping them to combine these two things. In addition, the viewpoint of Professor John Mulvey is sharp and indicate directions for applying ML in investment management courses. Best course ever.
by Andrea C•
John part is really confusing and not well explained. his slides and very high level and labs are very low level with basically no explanation. The rest of the course is fine.
by Nicholas P D•
The first two courses were very well done. This one is not even close to helpful. In the first two courses the Jupyter lab sessions were my favourite and really brought all the concepts together. The prof would go step by step through the code, even if it took an hour. In this course, I completely dread the lab sessions. They are only 15 minutes long and dump 200+ lines of uncommented code on you to deal with yourself. Also, it would be really nice if they could add presentation slides. All the lectures take twice as long because I have to pause and write down the formulas. It's sad because I used to look forward to learning, now I am just here to finish the specialization.
by Tommy L•
This course is absolutely horrible. Large majority if not all of the content is just fluff. The quizzes have very little to do with the lectures or labs. Also some of the quiz questions are just wrong or are irrelevant. The code in the labs is low quality. The lecturer is bad at teaching and explaining concepts.
by Michinori K•
This course is clearly of lower quality than the previous two courses of the Investment Management with Python and Machine Learning Specialization. Quiz is too ambiguous and very painful to pass.
This is the worst course of this 4-courses specialization due to the useless lab-session. I miss VJ so badly....lol
by Erick I A•
It was an amazing course, but definitely I will suggest for you that want to take this course to have a knowledge of investment, statistics and python. I totally recommend this course.
Excellent course, very helpful for my research work
by anurag j•
Please consider adding additional videos for the lab sessions, as one can not gain the Machine Learning python coding skills from PPT slides!
by Jerry H•
What I found to be really valuable and potentially useful were the examples/case histories of how the various machine learning techniques to portfolio management. For me, the most valuable learnings were, regularized regression to compute factor loadings, application of PCA/Clustering and Graphical Approaches to maximize portfolio diversity, and scenario/regime based portfolio models. I fully intend to do some follow-up work in applying those techniques to my personal investment management. So while perhaps not as learner-friendly as the previous two courses, I think the subject matter will prove to be far more valuable if one invests the time after the course.
I think if you want a better understanding of the many machine learning techniques, you might be better served to take a course specifically focused on that. I found the treatment of these techniques, insufficient to gain a solid conceptual understanding of the techniques. With that in mind, the course might be improved be spending even less time on introducing some of the basic machine learning methods / and traditional models, that are well covered elsewhere, and more time on the case histories, and application of the methods to portfolio management and investing.
by Fabien N•
I have been more and more frustrated with the course that became less and less explanatory, but more and more descriptive. I still find the topics very interesting, and the first two MOOCs were really amazing, but I find this one much less clear and giving us much less understanding of the coding part. What would be really great would be to get a full description of what the code does, at least much more detailed than at present. As an example, no code was even provided for PCA and graphical networks, that's quite disappointing.
by Kevin B•
I think the ideas related to this course are interesting, and in concept it's a great follow-on to the previous two. Unfortunately, I don't believe anyone who doesn't already know concepts and techniques of machine learning will come away from this course with any understanding whatsoever of what they are. I am a mentor for a Coursera specialization in Deep Learning, and I found the description of supervised and unsupervised learning here to be unintelligible. I'll be working through the lab code on my own to learn how to use it for portfolio construction, since I didn't bring that away from completing the course. Really a disappointment after the first two courses in the specialization, which I now question whether I will bother to complete.
by Piet Y•
Lectures were very confusing, poorly explained, poorly structured. Quizzes and tests were extremely bad: questions with often no link to the explained theory, many questions where you could seriously debate about the right answer.
The content was mostly limited to a few cases: a lot about factor shrinking, or better estimations for factor loadings, and a second case of recession prediction. Except for these two, most of the content was vague theoretical examples.
Labs were mixed quality: code was sometimes very clean, sometimes less. The tutors of the labs were sometimes giving a really clear rehearsal or overview of the topics (far better than the gentlemen who give the lectures), but sometimes they just read the text without any contribution.
Overall this MOOC was very disappointing. I have not learned a lot, and most of what I learned I had to google and research myself because the MOOC was too confusing.
by Kasper U•
Unfortunately, not nearly as good as the other MOOCs. Video sessions very "high level" and lab sessions extremely short. For a learner it was really hard to gain anything except from a conceptual understanding. Not bringing the learner anywhere near to implementing nor understanding the underlying mechanics. Additionally, for a non-Python person it was absolutely nonsense. No explanation of the code. Do data handling. No hands on... All in all a sad experience compared with MOOC 1 and 2.
by ALI R•
According to risk.net, Princeton University (Bendheim Center for Finance) is the best school in the world in the field of quantitative finance and the content of the course was very rich in my opinion, especially with that recently updated/added lab session. I would like to appreciate that new content. But there are a few problems for students that can be easily solved. The first problem is that some questions in the quizzes are confusing and there is nothing in the course material regarding them. The second problem is that some of the references, especially papers and reports are not available easily for further study. On MOOC1 and MOOC2 we don't have this problem. The third problem is that the students need more in-depth training on the ML techniques used in the course as most of them are new to ML field. Referring to a book is not a good way of training. The fourth problem is about the Labs. The course Labs need someone like Vijay as was in MOOC 1 and 2. These points are from a lazy student's perspective. I, personally believe that course is very rich as it presents real applications of the finance world and students can gain a lot if they consider the course demanding their further effort on learning ML and playing around with the data and codes. So, if we consider the course demanding which is not possible for every student, It is a perfect complement for MOOC1 and 2. So, I would like to thank you professor Mulvey, and lovely Lionel. Students should be grateful to you. In the end, I would like to ask this course developers to add more real applications to the course.
by Alejandro d H D•
The course is not an specialization on machine learning. It is a trip over the state-of-the-art machine learning techniques and how to apply them to financial data. You should have some previous knowledge about machine learning if you want to go through this course. If you dont have any previous knowledge, the course offers references to all the algorithms studied. Overall, a great explanation of the application of those techniques to the financial markets.
by carlos j u•
Super interesting, very well explained, with lots of useful resources (links to various papers and textbooks), and, best of all, with very practical, well-annotated notebooks applying the theory covered in the video lessons.