How to Predict Stock Prices with Scikit-learn (Python tutorial)

In this Python tutorial, Caelan will show you how to use Scikit-learn to predict Tesla's stock price by training and testing a long short-term memory (LSTM) neural network model. This same machine learning technique can be used to predict tomorrow's stock price with only minor modifications.

***************************************

***************************************
ADDITIONAL RESOURCES:

6 Python Tips and Tricks YOU Should Know ►

Push- Up Bot?! Make a Discord Bot in Python [step-by-step tutorial] ►

How to Build HANGMAN in 10 Minutes (Python tutorial) ►

***************************************
Don’t forget to subscribe :)

STAY TUNED:

[gautamj]

The min max scaler is being fitted on the entire dataset. This means that you have essentially leaked information about the test data.

The proper way to do this would be to first split your data into train and test set. Fit the scaler on train set only. Transform train and test set afterwards.

[simonroth]

This is basic coding (only) and has nothing todo with stock predictions guys!

[jessemeekins]

where did that "T.astype" come from on line 10? Undefined variable? cant figure it out

[mayacho]

Inflation depreciates idle money. I'm in a privileged position to be able to save almost 65% of our net household income, as I placed it on safer investments. The key for us was not spending beyond our means. If you invest and have other sources of income outside of dividends then you will be able to live off dividends. Got north of $520K in my portfolio as I bought a lot of dividend stocks before, I'm buying more now, and I will buy more when it drops further.

[codenerd]

Thank u Kite for making learning Fun and Easy

[codenerd]

Trust me everyone, you can learn more here

instead of other tutorials on internet

[JorgeGiro]

The repo link points to a voice-recognizer?!

[daxbradley]

Why is this referred to as predictions, when it appears that the ML was able to learn the last 100 days (or however long the training + test set is) and effectively normalize the curve.

I don't see how it predicted anything, which implies looking ahead

[tobedeleted]

What If you had a machine learning algorithm. Which took like all common elements such as insider trading publicly available data or historical price points. And could predict with a higher certainty about the stock prices ?

How effective is your model of prediction compared to linear regression or like standard deviation + avg

[Youssif_Hamed]

I'm sorry what T mean in code what is the defend for her ?

[mostafaamer]

Hey man is it possible that you show us a tutorial for multivariate rnn to predict stock prices?

Thank you.

[DanielWeikert]

thanks. should not you make the time series stationary first? When you reshape X_train should not it be ( shape[0], shape[1], 1)
Great channel and tool by the way

[probablyhomer]

Doesn't work. You will get a never ending loop of bugs to fix encoding, value errors, int()errors, etc. etc. etc. Unless you have the exact same file as he does, you're in for a Bug nightmare trying to fix Byte/UTF/ascii/latin-1 errors.

[CyborgGaming]

He never defined T. What is T, his train data?

[stavrosgourtziades]

8.45 batch_size=???? i cant see if its 2 or not

[DhavalPatel-hcwo]

thx it helped me a-lot u deserver a sub and like and pls do more videos can't wait to see them

[dukfly]

NameError: name 'T' is not defined

[ticuu]

Didn't understand a sh1t but like it anyways

[shekharkumar]

Super fast .Go bit slow. Hope it's knowledge sharing not website publicity

[boggeshzahim]

You open your mouth so wide when you talk