Skip to content

Using the Scikit Learn library to predict stock prices as regression problem

Notifications You must be signed in to change notification settings

Pizajolo/regression-sklearn-stockprices

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

regression-sklearn-stockprices

Using the Scikit Learn library to predict stock prices as regression problem. This is just trying different regression methods on stock data. With a model like this it's not possible to predict the future of the stock marked. If it would be that easy we all would be rich :D

Results:

As you can see in the results of the Notebook even if the models seem to be not to bad, they are. So if you look closer, they just mimic what happend the day before. From that we can see that a regression model is not good enough to predict stock prices. To do that you should try to use other models and most important its not enough to use only past stock data. There for you could try to use Sentiment Analysis on twitter or news data to improve the model.

About

Using the Scikit Learn library to predict stock prices as regression problem

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published