Skip to content

ML program that can predict whether someone will click on an online ad as it crucial for understanding how well ads are doing, which is important for search engines.

License

Notifications You must be signed in to change notification settings

bcsamrudh/Click-Through-Rate-Prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Click Through Rate Prediction

Coursework Project, Learning with Imbalanced Data

ML program that can predict whether someone will click on an online ad as it crucial for understanding how well ads are doing, which is important for search engines.

Model Architecture

Model Architecture

Dataset

Avazu Ads Dataset

Class Imbalance : There are less number of clicks on ads compared to non-clicks

Attributes : click: non-click/click , site_id , site_domain , site_category , app_id , app_domain , app_category , device_id , device_ip , device_model , device_type , device_conn_type.

Imbalance Learning Strategies Used

  • SMOTE
  • Oversampling
  • Undersampling

About

ML program that can predict whether someone will click on an online ad as it crucial for understanding how well ads are doing, which is important for search engines.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published