Chevron Left
Back to Python and Machine-Learning for Asset Management with Alternative Data Sets

Learner Reviews & Feedback for Python and Machine-Learning for Asset Management with Alternative Data Sets by EDHEC Business School

4.4
stars
229 ratings

About the Course

Over-utilization of market and accounting data over the last few decades has led to portfolio crowding, mediocre performance and systemic risks, incentivizing financial institutions which are looking for an edge to quickly adopt alternative data as a substitute to traditional data. This course introduces the core concepts around alternative data, the most recent research in this area, as well as practical portfolio examples and actual applications. The approach of this course is somewhat unique because while the theory covered is still a main component, practical lab sessions and examples of working with alternative datasets are also key. This course is fo you if you are aiming at carreers prospects as a data scientist in financial markets, are looking to enhance your analytics skillsets to the financial markets, or if you are interested in cutting-edge technology and research as they apply to big data. The required background is: Python programming, Investment theory , and Statistics. This course will enable you to learn new data and research techniques applied to the financial markets while strengthening data science and python skills....

Top reviews

AT

Mar 5, 2020

really interesting applications and good examples. More breadth than depth but a great guide as to what the state of the art is in applying machine learning to more alternative forms of data.

BB

Mar 30, 2021

Was pretty informative, especially getting to see and understand the techniques that large hedge funds might use to determine their investment strategies.

Filter by:

1 - 25 of 60 Reviews for Python and Machine-Learning for Asset Management with Alternative Data Sets

By Loc N

•

Jan 4, 2020

Way better than the third course in the Specialization. If I have to rank the courses in terms of the organization from high to low, the ranking would be: the first course, this course, the second course, and the final course.

By Fabien N

•

Feb 6, 2020

Amazing course ! I had been a bit disappointed by Course 3 of the Specialization, but this Course 4 clearly paid back ! The 3-sections structure for each week is really great, the theory is well explained and the lab sessions are very clear, this allows us to really grasp the concepts and be able to use them in the future. In addition, the research application sections greatly open the applications to advanced studies and increase curiosity for the topic. Congrats ! It's one of the best MOOC I had to follow!

By Marco K

•

Jul 12, 2020

The first two courses have raised the expectations to a very high level. The last two courses don't meet them at all. Difficulty with modules working (basically lack thereof) makes it difficult to really learn something here.

By Rehan I

•

Apr 13, 2020

The course is quite good, but the labs were quite rushed - students would benefit from going through the notebooks in more detail with the teachers. Secondly, the 'Application' sections had no accompanying notebooks/labs - students would benefit from being able to replicate some of the findings in the research, at least those of the research by Gideon.

By Andrea C

•

Jan 16, 2020

theory and lab not really synced. Lab not adding lots of value.

By carlos j u

•

Nov 1, 2020

Trully amazing in the breadth of topics covered: sentiment analysis of corporate filings (nltk), network analysis using tweets data (networkx), consumer behaviour estimation using geolocation data (folium) and more.

While the depth of the analysis was not too deep, it was deep enough for the analyses to be somewhat complex, smart, and for there being some space where nuances and future work could be commented and suggested. This is perfectly understandable by the trade-off between depth and breadth for a course of reasonable length.

I would have loved to see an explicit development or discussion of some methods to connect the insights derived from these alernative data sets to actual predictions of volatility, returns or (even) asset allocations. For me that was the only thing missing in this MOOC. How I would go from, let's say, a local trend in sentiments for a given set of companies to decisions on how should I invest in those companies. Having said that, this course is awesome and I really recommend it to someone feeling comfortable with Python scripting, pandas and numpy.

By Antony J

•

Oct 15, 2020

This was a superb course, hosted by Gideon, an academic / practitioner who has published in the very best peer-reviewed journals (Journal of Financial Economics and Financial Analysts Journal) and Sean, a talented quant who does a fine job of walking through state-of-the-art techniques in Information Retrieval. I loved the Python library that converts geolocation data into maps, for example!

This is a fine conclusion to an amazing specialization. Thanks!

By Alex T

•

Mar 5, 2020

really interesting applications and good examples. More breadth than depth but a great guide as to what the state of the art is in applying machine learning to more alternative forms of data.

By Brian B

•

Mar 31, 2021

Was pretty informative, especially getting to see and understand the techniques that large hedge funds might use to determine their investment strategies.

By Runar O

•

Mar 6, 2020

Excellent view into modern financial research in the use of alternative data sets including valuable demonstration in implementation.

By Kevin W

•

Apr 2, 2020

Great material and knowledgeable lecturers.

However, the Lab sessions aren't relevant to completing most quizzes. So to get more out of the course the student must play with the code outside the context of the class. The disconnect between the two seems like a missed opportunity to force students to look objectively at the Labs and its application.

By Vadim T

•

May 22, 2020

It is a very good course which actually gave me a lot of ideas for my graduate research.

I am giving three start because there are no programming assignments. Quiz questions are based on the in-class labs but no opportunity is provided to play with numbers and to write your own code.

Nonetheless, excellent continuation of the sequence (unlike course 3 which is useless).

By Jerry H

•

May 20, 2020

While not immediately useful for me, I found the course very enlightening. While I was aware of alternate data and its application, I did not have an intuitive feel for how it was done. The course gave a nice introduction to that. Appreciated the coding labs (code is well commented, so I have an excellent resource to help improve my coding knowledge ability). Only suggestion is to rely more on matrix multiplication (as in the last lab) which will make it easier to understand the code and understand the approach being used.

Really liked the structure of the course: 1) theory, 2) labs and 3) application and the links to the many excellent papers. This was a great course structure for people who want to apply the the material.

By Dirk W

•

Feb 5, 2020

Very well-constructed course, right balance between theory, lab sessions and application. Theory to the point. Lab sessions largely detailed, which is really a forte. Really interesting readings in the application section. Quizzes adapted to the theory, lab sessions and application. No technical issues.

By Hernan S L

•

May 1, 2020

Great Course! Both guys were awesome! I find the subject really interesting, though I think is hard to get that data. I would really recommend it!

Thanks

By Ravi T

•

Mar 22, 2022

It was alright. Programming lab work is the only thing useful.

By Kenneth N

•

Jul 14, 2022

Excellent material. but labs requires more clarity

By ALI R

•

Jun 23, 2021

The course surveys the most important approaches for financial alternative datasets. It will give you a framework for how to see and explore this type of data, build hypotheses and test them. It is highly recommended for everyone in the field of financial data science. Another great course from EDHEC.

By Inna P

•

Nov 14, 2020

This is a great course for finance practitioners - while some of the technical concepts behind the code might not be explained in very deep detail, the code provided gives you opportunity to jump straight into experimenting with the datasets and models around asset management.

By Alessandro F

•

Jan 8, 2023

Insightful and well organized course. The combination in each chapter of theory, lab and application made by high level practioners is very valuable. 100% recommended if you are interested in the subject.

By Michinori K

•

Feb 20, 2020

Great course! Highly relevant and including latest research topics.

Both lectures and labs are very efficient in delivering state-of-the-art contents.

By Yaron K

•

Oct 3, 2020

Detailed Python notebooks clearly explained give valuable tools for analyzing data, and the lectures give ideas what to do with the analyzed data.

By Jesse L

•

Apr 19, 2021

Very In-depth technical and informative. Very interesting to integrate data analysis with the current practice in investment management

By Lucas F

•

Apr 30, 2020

Very interesting course. Instructors are quite good. The graded quiz could be less theoretical and a bit more practical/applied.

By Karl J

•

Nov 23, 2020

Great overview of how nontraditional data has been applied to finance. The programming aspect of it was very well-done, too