Skip to content

Soad-Afify/365-Data-Science-Challenge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

365-Data-Science-Challenge

A Neural Network model using Keras to predict whether a Free Plan user would convert to a paid subscriber or not:

Add calculated columns per student before merging all needed data into one data frame. Dropp unneeded data and drop all very low correlated features with the y variable column. Use Stratified Random Sampling based on the highest correlated features with the y variable data. Use StandardScaler to strandardize X values. Create neural network model using Keras. Get Loss and Accuracy as below:

  • Training: loss: 0.0633 - accuracy: 0.9841
  • Validation: val_loss: 0.0630 - val_accuracy: 0.9840
  • Test: loss: 0.0689 - accuracy: 0.9826

About

365 Data Science Challenge

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published