Chevron Left
Back to Guided Tour of Machine Learning in Finance

Learner Reviews & Feedback for Guided Tour of Machine Learning in Finance by New York University

3.8
stars
663 ratings

About the Course

This course aims at providing an introductory and broad overview of the field of ML with the focus on applications on Finance. Supervised Machine Learning methods are used in the capstone project to predict bank closures. Simultaneously, while this course can be taken as a separate course, it serves as a preview of topics that are covered in more details in subsequent modules of the specialization Machine Learning and Reinforcement Learning in Finance. The goal of Guided Tour of Machine Learning in Finance is to get a sense of what Machine Learning is, what it is for and in how many different financial problems it can be applied to. The course is designed for three categories of students: Practitioners working at financial institutions such as banks, asset management firms or hedge funds Individuals interested in applications of ML for personal day trading Current full-time students pursuing a degree in Finance, Statistics, Computer Science, Mathematics, Physics, Engineering or other related disciplines who want to learn about practical applications of ML in Finance Experience with Python (including numpy, pandas, and IPython/Jupyter notebooks), linear algebra, basic probability theory and basic calculus is necessary to complete assignments in this course....

Top reviews

LP

Oct 22, 2021

Very useful course. Personally, I think that there should have been more focus on the implementation of tensorflow and neural network codes. Overall the course is well structured and very clear.

KD

Aug 23, 2019

Introduction of ML for Financial application with combination of Scikit learn, Statsmodels and Tensorflow with neuralnets made this class very interesting. Learned and Enjoyed lot.

Filter by:

26 - 50 of 206 Reviews for Guided Tour of Machine Learning in Finance

By Mayank J

•

Nov 17, 2019

The coding part could have been better explained and the reasoning for what is being done should be included in the coding videos.

By Frederic B

•

Nov 5, 2019

Fantastic lectures, great first programming assignments with unfortunate tail quality of the programming assignments

By christopher s

•

Oct 29, 2019

The lectures were Ok and the course assignments were Ok as well, but they had very little to do with each other. The course and ideas have so much more potential than was provided with this class. It is very unfortunate.

By Zhen C

•

Oct 26, 2019

Lectures are good. Exercises are confusing, kind of irrelevant to the lectures and do not have any information about the underlying data. Sample codes are useful though.

By Artem S

•

Aug 19, 2020

I read the reviews by others before submitting mine. I agree that (1) the lecture material is very informative and of good quality, (2) assignments are sometimes hard to follow, but I have seen much worse on coursera in other courses (from Columbia, for instance). (3) Some people complained about professor's accent, he does have a fairly prominent Russian accent, but everything is still very much understandable and you can't hold something like this against him. (4) Some people claim that although they "have a strong math background" the material in lectures is intentionally made sound hard. I have a math background too and found his explanations very intuitive. My undergraduate math treatment of related topics was much more rigorous that this. (5) Others complain about there being too much math/many equations in lectures. ML is about math, if this tiny bit of mathematical rigor is too much for you, you should not be doing ML. (6) To my surprise, some people are wondering who are the target audience. The professor clearly states that the audience for the class is people with ML background willing to learn some financial applications. This is not really to teach you ML from scratch, but to introduce ML professionals to the field of finance. In my opinion, the professor succeeds in this and gives a list of good references for ML theory too.

By Jong H S

•

Jul 27, 2018

This is an excellent course bringing together machine learning and finance. The content and exercises are just nice as introduction to both subjects. The clarity of contents presented in relating these 2 are timely and commendable. The Jupyter notebooks were a little buggy with some annoying glitches in the beginning but things are all ok. The descriptions in Jupyter on what the students need to achieve probably need a bit of polish. Overall a 5-star. Great job to Professor Halperin and team.

By Wian S

•

Aug 22, 2018

I absolutely love the depth that this course goes into by providing in-depth reading materials and citing advanced sources in videos for further research. Although some other reviews say that the assignments are too hard and no guidance is given, I think this is an advantage because a lot more learning goes on. I've taken other courses where all that you have to do is fill in about 10 lines of code for the entire assignment after 10 paragraphs of explanation and it really kills the learning.

By Jacques J

•

Nov 11, 2018

At first I was irritated that some of the material wasn't covered in class but when I read all of the recommended reading then it became more clear what to do. This course takes time and attention. Its not an introduction course, its more an an intermediate course. I was impressed with this course as it directly relates to applications in finance and helped me to see how to apply algorithms I already know to finance. It also gave me a bit more mathematical rigor.

By Wenxiao S

•

Feb 23, 2020

Perfect courses with challenging assignments. Together with recommended references, I learned a lot in machine learning, both about algorithms itself and applications in finance. Through the course, I finally understand ML is NOT a black box, but an optimization methods based on probability theories.

I really love such research, and I will complete the whole specialization without doubt!

By Dima S

•

Nov 13, 2018

I liked this course. It extends your knowledge regarding such basic algorithms as linear/logistic regression, gives some useful practice with TensorFlow. But, I would definitely recommend everyone, who didn't understand the material go through it again and read recommended materials after each week. Otherwise, such lack of understanding will be like a snowball.

By Joaquin T

•

Jul 18, 2018

Except for a few issues with assignment submission the course material and exposition and recommended readings were excellent. As a disclaimer, I have taken non-financial ML courses in the past, though, so I do have some background knowledge on tensorflow. That might influence my opinion.

By Vasco C

•

Jan 25, 2020

Excellent course, but be prepared for hard work. It's an intermediate level not an introductory course. It would be better if the assignments were better documented - it's true that we should get used to do our own research but that significantly increases the scheduled work load .

By Angelo J I T

•

Aug 3, 2019

While this course gets a lot of negative comments due to the inconsistencies between the exercises and the actual material, it taught me a lot about the probabilistic models behind popular machine learning algorithms. Also learning to do things in tensorflow is a great bonus.

By Enzo G

•

Aug 28, 2018

This is a great course, I really learned the topics. Some people has made bad comments regarding the programming assignments difficult. But really is this difficulty what help to go deeper in the topic and conect the theory with the practice. Excelent!

By MARLON F

•

Dec 22, 2019

Well, the lessons are amazing. But the projects are very difficult and not so related to a better learning curve. Do a linear regression in 100 ways and thousands tools doesnt make difference. Could approach only one, but focused.

By sudipto m

•

Aug 15, 2019

Really good content which is pretty focused and at the same time pretty generic. Totally perfect for someone who has python coding experience and some interest/experience in finance and ML. No prerequisites in ML/Finance required.

By Ziyuan L

•

Feb 17, 2023

learn useful programming code for business related data but I am still a little bit confused about the mathematical and theoretical part like MLE, Prior, posteriors, and Merton model and so on. In short, it is a great class!

By Chazz E

•

Mar 29, 2020

The course is challenging unlike other Coursera courses, you need to learn TensorFlow if you want to pass the programming assignments. Some out of course studying was involved to complete the assignments as well.

By Juan S

•

Jan 17, 2019

This course is a perfect introduction to machine learning applied to finance, which covers the essentialtopics that students must know to deepen their knowledge in this fascinating field.

By Krishna D

•

Aug 24, 2019

Introduction of ML for Financial application with combination of Scikit learn, Statsmodels and Tensorflow with neuralnets made this class very interesting. Learned and Enjoyed lot.

By Kenneth N

•

Jul 26, 2022

Great course. but requires lot of patience. Uses lot of unnecessary symbols and equations to explain concepts. Overall it is a good overview of the big picture of ML in finance.

By Eduardo C

•

Mar 5, 2019

Excellent! it is very wider and get to be so clear at the same time. It was an amazing experience specially because I am returning back to Coursera courses.

By Arka B

•

May 28, 2018

Exceptional disposition and lucid explanations! Ideal for a Risk Management professional to sharpen machine learning skills!

By David W

•

Sep 9, 2019

Leans heavily on explaining differences between tech and finance applications of ML, but still great!

By Roman V

•

Dec 2, 2023

Nice, but update the version of tensor flow or provide special pdf file with 1.10.1 documentation.