Labs Malfunction

你对得起我们吗？日内瓦退钱

It's an exceptionally difficult task to predict financial time series, and even harder to design an automated trading methodology that can take into account those forecasts while monitoring the trading environment (trading costs, other traders, sentiment). This final course is an ambitious attempt to expose learners to the most advanced concepts in the field.

To be able to comprehend the Reinforcement Learning materials appears to require expertise in deep learning far beyond sequential models, and also appears to need the volume and integrity of data only available to high-frequency trading firms. Thumbs up to the specialization curators for providing a non-trivial introduction.

The module that rescued the course (and lifted my rating to 5 stars) was the AutoML demonstration. I was reassured to see that Gradient Boosted Trees were chosen as the appropriate methodology, as this is what I have casually observed as being the most effective methodology in use today for end-of-day data problems. Looks like an amazing product, if you have the money!

Succinct and great explanation of deep reinforcement learning methods with amazing demo lab scripts

It's Intensive and Inclusive, but please make sure all labs work smoothly.

This content really is ahead of the Business As Usual.

Congrats!

Need more time to finish the ML model

Muy buen curso.!

perfect!

Provide the idea and method of RL for trading, but seems like less practice knowledge for the trading. hope can add more detail for for the trading build up. overall the course are good.

Great course, exactly what I was looking for! But there were some technical difficulties on practical tasks ...

I look forward to examples of integration of decision based on reinforcement learning and algo-trading logic

A touhg and very advanced course, with an amazing Google Cloud Platform !!!!

Nice with the RL classes, it is a bit random.

I learned a few cool things. The main problem with this specialization is that the Machine Learning Stuff and Finance stuff are really separated (Google, NY univ). What I was looking for is the place where two concepts meets. Also i felt like ML stuff went too deeply too fast. Still... Cool Introduction.

It is geared more towards people who already have an understanding of the stock market and its lingo. Not much information about stock market lingo for a beginner.

Lab is obsoleted... and the practice doesn't give you any advice and the packages doesn't work due are very old or not anymore mantainance

While there were a lot of interesting concepts in this course, I didn't feel that I learned a lot from it and certainly was nowhere near implementing what I wanted to. It pushes Google's cloud services so you're on your own if you want to program on your own computer. I've since completed a course by deeplearning.ai (not trading focussed) which I felt was a lot better, I learned a lot of theory to develop an understanding of what they're teaching as well as practical coding assignments that I felt I could actually take the code and apply to my own projects.

Google pushes its ability to learn from BigData but I really don't consider stock data to be BigData, at least if you're processing a single instrument/currency/stock at a time. If you're trying to go down to tick level data then you're going to have more problems with lag and execution making processing that amount of data a bit pointless... unless that's really really what you want/need to be doing.

To be fair to this course, it is good to know what is out there should it be suitable for your challenges and yeah, they can process a massive, huge, gigantic amount of data very quickly.

Trading part is okay, but the reinforcement learning part is terrible. Not only the contents are a lot, the instructor speaking pace is too fast, with a high pitch. She might be passionate about RL and very experienced, but it does not mean she can teach others that way. Besides, all the labs do not work for me, with deprecated packages and code. This course should be updated or removed from Coursera.

Some of the notebooks used in the course are outdated, and thus the "labs" are not really functional

Most labs codes had errors and could not even load data. Unable to practice with labs like that.

Few financial applications. RL is a complex notions. Exerices are too difficult.

not really make me statisfied