Model validation and bias removal in quasi-experimental testing of mobile applications

US10304067B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Ya Xu · Mountain View, US
• Nanyu Chen · Sunnyvale, US
• Bryan Ng · Ithaca, US
• Weitao Duan · Mountain View, US

Key dates

• Filing date: Apr 27, 2016
• Grant date: May 28, 2019
• Expiry date: Mar 5, 2037

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q50/01
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

The disclosed embodiments provide a system for evaluating a performance of a mobile application. During operation, the system obtains, for a statistical model used in a quasi-experimental design, a first predicted outcome produced from a first set of data that is collected from two substantially identical versions of a mobile application. Next, the system uses the first predicted outcome to assess a bias of the statistical model. The system then improves an accuracy of the statistical model by using the assessed bias to normalize a second predicted outcome of the statistical model.