Cryptocurrency-predicting RNN intro – Deep Learning w/ Python, TensorFlow and Keras p.8



Welcome to part 8 of the Deep Learning with Python, Keras, and Tensorflow series. In this tutorial, we’re going to work on using a recurrent neural network to …


26 Comments

  1. Your videos are absolutely fantastic- the presentation, the bite-sized information, and complete python code.

    Just one suggestion regarding the targets/labels: I would include twice the trading cost and some sort of margin.

    Thank you very much for this series. I watching every one of the videos.

  2. Thank you for creating this video, this is well explained and so easy to follow.
    There are so many ways to create the target column but I used the below, just in case some like to use pandas apply function the code snippet is below:
    main_df['target'] = main_df.apply(lambda x: classify(x["future"], x[f"{RATIO_TO_PREDICT}_close"]), axis=1)

  3. ur the biggest alpha male god ever made, I BET THE DEVIL BOWES TO YOU AS HE CAN SEE YOU ARE BORN FROM GOD AND BY JESUS AND THE LORRRRDDD
    I WOULD OF TAKEN THE MONEY I EVER GAVE TO SCHOOL
    AND GIVE IT TO INDEPENDENT ONLINE TEACHERS LIKE YOU
    SRSLY, YOU HAVE STARTED AN EDUCATIONAL REVOLUTION
    YOU HAVE MADE TEACHING AVAILBLE, FREE AND BETTER

    AMEN SENTDEX!

  4. Hey. That was a great series, thanks for that. I have a good and well trained model but i don't know how to put that to work using model.predict(). I can load it and see its summary, just can't generate any output that makes sense. Could you please make one more video of this series where you simply use the model you have generate?

    Thanks

  5. Hey Sentdex, if I am using a time series data set and simply want to use the RNN to predict outliers, or something out of the norm, I obviously would not have an exact "prediction" of a binary case as in the example of the future being greater than the past price. Any ideas of how I would use the RNN to predict outliers without a predefined rule? Thank you again for all of the videos!

  6. Bitcoin and other crypto-assets are historically known for their wild and explosive volatility. But that’s not at all been the case for several weeks now, leading to boredom in the crypto mamarket.It�s caused traders to get shaken out or move to the sidelines, or as we’ve seen, move onto altcoins. Altcoins everywhere have been surging, with a few setting new all-time high price records.But because things have become so stagnant in Bitcoin, is has prompted crypto analysts to dig into a technical analysis tool and I can proudly say Mr. Steve Hayward strategy is the best tool one need to make a successful trade on Bitcoin with profits I’m a full time student to his online course of which I started 30days ago I started with the mindset of making $20,000 but wow to my greatest surprise I made $78,000 with the 98.9% accuracy his signals comes with and I started with the initially with &5,700 and it’s just surprising how much profit I made and I can say how he’s indeed a guru in trading bitcoins .. he’s contact info are (stevehayward92@gmail.com) or WhatsApp [+1 914-301 6142]•

Leave a Reply

Your email address will not be published.


*