Skip to content

Future sales prediction problem, with the use of advanced entity embeddings based neural network. This notebook also shows how to deal with very big datasets in pandas, and finding sense in the data.

Notifications You must be signed in to change notification settings

pedrito87/future_sales_pearson

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

future_sales_pearson

Future sales prediction problem. This is quite a unique project, as the data we are provided with requires a lot of work, and leaves a lot to the Data Scientist's imagination.

This notebook shows how to deal with big datasets in pandas in a couple of lines of code, and finding sense in the data, through visualising data in matplotlib.

The most special part of the project lays in the model creation part. I create an advanced entity embeddings based, neural network with multiple inputs model, especially tailored for the problem at hand.

You can find the description of the challenge, and download all the necessary data at: https://www.kaggle.com/c/competitive-data-science-predict-future-sales.

About

Future sales prediction problem, with the use of advanced entity embeddings based neural network. This notebook also shows how to deal with very big datasets in pandas, and finding sense in the data.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published