Chevron Left
Вернуться к Introduction to Trading, Machine Learning & GCP

Отзывы учащихся о курсе Introduction to Trading, Machine Learning & GCP от партнера Google Cloud

4.0
звезд
Оценки: 724

О курсе

In this course, you’ll learn about the fundamentals of trading, including the concept of trend, returns, stop-loss, and volatility. You will learn how to identify the profit source and structure of basic quantitative trading strategies. This course will help you gauge how well the model generalizes its learning, explain the differences between regression and forecasting, and identify the steps needed to create development and implementation backtesters. By the end of the course, you will be able to use Google Cloud Platform to build basic machine learning models in Jupyter Notebooks. To be successful in this course, you should have advanced competency in Python programming and familiarity with pertinent libraries for machine learning, such as Scikit-Learn, StatsModels, and Pandas. Experience with SQL is recommended. You should have a background in statistics (expected values and standard deviation, Gaussian distributions, higher moments, probability, linear regressions) and foundational knowledge of financial markets (equities, bonds, derivatives, market structure, hedging)....

Лучшие рецензии

MS

29 янв. 2020 г.

Excellent! But, I am missing some of the prerequisites since I just wanted to take a chance and try things out, but feel like proceeding further might lead to some stumbling blocks.

AJ

20 нояб. 2020 г.

I thought this was excellent. Some familiarity with standard SQL is needed to get the most benefit from the materials, and the course is clearly aimed at GCP users.

Фильтр по:

26–50 из 195 отзывов о курсе Introduction to Trading, Machine Learning & GCP

автор: Atichat P

28 дек. 2019 г.

Good

автор: Meisam M

24 дек. 2019 г.

some explanation in trading was hard, it was realy good to be able to test google cloud services, but needs more practical examples

автор: jamesguo

15 февр. 2020 г.

a bit too easy, looking forward to next courses

автор: Albert W D P

13 янв. 2020 г.

I have taken multiple courses on Coursera. This course had particular strengths and weaknesses. For strengths, I certainly learned a fair amount from the course, particularly as it applied to ARIMA models for finance. For weaknesses, the course seemed to have been somewhat haphazardly thrown together. Week 4, the last week, was particularly poor. The lectures had little to do with one another and appeared pulled from multiple other sources. One was geared for people with advanced skills in mathematics and machine learning and was way out of my, and most people's, wheelhouse for learning.

автор: Silviu M

27 дек. 2019 г.

Rather good content but I believe it is not always presented in the right order. In addition, some of the revision questions were extremely superficial. Last, I really don't like lecturers reading out the content from their laptops. I can do that by myself!

автор: MohammadSaied A

12 июня 2020 г.

I generally have high respect for whoever teaches me something useful, but I have to tell my try opinion here. Maybe passing other online courses has risen my expectations, and that it the reason I give two stars to this course. So here are my critiques to this course: 1- The contents are at different difficulty levels in this course, for example, the explanation on ML are very elementary, while the programming assignments are for advanced programmers proficient in SQL, Python, BiqQuery, ...

2- The material is not coherent. It doesn't start with general and straightforward explanations and then gradually elaborate on the details—3- The method of lecturing. I had to close my eyes while listening to some of the lecturers because the way of lecturing is very unnatural, and it is a distraction. Sometimes watching the presenter helps in learning because you can connect to their mind, but sometimes their hand movements, gestures, the way they look at the camera, and all these things are simply distractions.

But I must also mention some advantages of this course. 1- You will learn about some keywords on the topic of Trading using ML. You can generally understand what's going on in this area and what are the tools being used. 2- You'll find some links to useful resources so you can self-study and go through the direction you desire.

Anyway, I am sure this course will gradually improve after feedback from learners.

автор: Oleksandr I

17 янв. 2020 г.

Almost no trading-related content (except the brief introduction in the 1st week).

ML content is poor comparing to other ML courses on Coursera. Instructors teach how to do simple ML tasks with some third-rate chargeable Google product (like SQL but with tweaks on it). In the course itself the product is free of charge, but why teach anyone to do this in paid software, when there is a lot of good open source solutions used in the industry?

Overall extremely poor trading and ML content is charged $50 per month, which is a too high price.

автор: Cesar V

16 июня 2020 г.

Sorry, this is a mess.

A frankestein of different coursers, you are much better with something like Quantopian.

автор: Martin S

30 янв. 2020 г.

Excellent! But, I am missing some of the prerequisites since I just wanted to take a chance and try things out, but feel like proceeding further might lead to some stumbling blocks.

автор: Ricardo B G

21 янв. 2020 г.

Maybe Week 4 can be Week 1. It has the description of the tools used in the rest of the weeks.

автор: Kar T Q

1 февр. 2020 г.

Excellent introduction

автор: Leonardo B

9 мар. 2020 г.

Great course

автор: Raguram S

8 февр. 2020 г.

Great Course

автор: Gabi M

2 февр. 2020 г.

Giving 4 stars as there were some technical problems with AI Platform in week 3 and could not access the lab work, which is pretty disappointing.

автор: Marcos F

21 янв. 2020 г.

A good intro to machine learning in finance. I does not goes very deep, but hat some useful exercises and practice with google cloud.

автор: Abby M

8 мар. 2020 г.

Great for beginners! A lot of examples and theories with practices. It let me learn more about the underlying principles.

автор: Manfred R

8 мар. 2020 г.

The instructors presented their topics very clear and understandable.

автор: Chaikit R

21 февр. 2020 г.

Good point to start, but need to clarify more in some points.

автор: Rodrigo L D

18 февр. 2020 г.

Good introduction to ML and GCP, shallow content on Trading

автор: Filip Š

2 янв. 2020 г.

Rather easy

автор: David G

9 июня 2022 г.

A collection of videos from other sources/courses, combined with some specifically for this course. A bit too basic for what I needed (not their fault).

Some minor complaints:

Audio quality/volume was a mixed bag, would be nice if they normalized audio across all videos.

Painful process to use the 'QwikLabs'. I mean, you couldn't make a clunkier user experience if you tried.

The course felt like an ad for Google products in parts. Instructions for how to use the Google products are now old so lots of menus have moved or changed names. So, not a very good ad because everything seemed more difficult to use than it should be.

автор: Холодков Ю

8 дек. 2021 г.

Не системные знания, просто какие-то обрывки

автор: Bryan D

13 янв. 2020 г.

Ok as an introduction (it is what the title says after all), but I ended up doing a lot of things in the lab without really knowing why I was doing them (e.g. loading different libraries, a lot of the syntax, etc.). Granted I can research that on my own, but more guidance would have been appreciated.

More broadly, this course feels a bit chaotic, jumping from one topic to the other, and then getting back at a previous one. This is ok to explore the fundamentals, which is clearly the intent here, but more structure would be welcome. Particularly, the introduction to Jupyter notebooks coming at the end of the course, after three labs, feels a bit frustrating. On a similar note, the course really feels like (and clearly is) something that was patched together from bits and pieces of other courses, with often times instructors referring to "previous" topics that were not actually covered (e.g. random forests). For a paid specialisation, this feels a bit sub-par. I have had free Coursera courses that felt more consistant.

автор: Yue C

11 янв. 2020 г.

I am a AI research engineer and I can follow the technical content without problem. But I can imagine students who are new to these topics would get lost very quickly. In my opinion, this course talked very little about the fundamentals of the models, and I don't think anyone would be able to understand these models by taking this course.

автор: Esteban Z

17 янв. 2020 г.

One could basically get a very high grade just copying, pasting and clicking SHIFT + ENTER