Browse Prior Art Database

A Method and System for Assessing Preserved Creative Quality Advertisements Based on Anticipated User Feedback

IP.com Disclosure Number: IPCOM000241964D
Publication Date: 2015-Jun-11
Document File: 2 page(s) / 91K

Publishing Venue

The IP.com Prior Art Database

Related People

Qiang Jin: INVENTOR [+3]

Abstract

A method and system is disclosed for assessing preserved creative quality advertisements based on anticipated user feedback. The method and system evaluates creative quality advertisement by predicting potential user feedback even before the advertisements are being served.

This text was extracted from a Microsoft Word document.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 53% of the total text.

A Method and System for Assessing Preserved Creative Quality Advertisements Based on Anticipated User Feedback

Abstract

A method and system is disclosed for assessing preserved creative quality advertisements based on anticipated user feedback.  The method and system evaluates creative quality advertisement by predicting potential user feedback even before the advertisements are being served.

 

Description

Disclosed is a method and system for assessing preserved creative quality advertisements based on anticipated user feedback. 

A good quality creative advertisement is a key feature to attract users to online advertisements as a bad quality creative advertisement may reduce user’s engagement, or even damage publisher’s reputation.  Advertisements feedback function enables user to provide feedback to advertisements to help improve user’s experiences.  However, advertisements feedback function provides advertisements quality measurement after the advertisements have been served.  Thus, the bad quality creative advertisement can still annoy users.  The method and system evaluates creative quality advertisement by predicting potential user feedback even before the advertisements are served.  

The method and system uses creative advertisement features and advertiser’s features as predictive variables and user advertisement feedback data as the target for creative advertisements.  The creative features may include meta data, creative tag, etc.

In an embodiment, the workflow is designed to have two stages, batch process and prediction process.  The batch process is scheduled to run offline on daily basis with a fixed time length of moving window.  A creative tester running in backend creates tags and fe...