18625830. CONTRIBUTION INCREMENTALITY MACHINE LEARNING MODELS simplified abstract (GOOGLE LLC)

CONTRIBUTION INCREMENTALITY MACHINE LEARNING MODELS

Organization Name

GOOGLE LLC

Inventor(s)

Xinlong Bao of Los Altos CA (US)

Ali Nasiri Amini of Redwood City CA (US)

Jing Wang of Mountain View CA (US)

Mert Dikmen of Belmont CA (US)

Amy Richardson of Santa Cruz CA (US)

Dinah Shender of Mountain View CA (US)

Junji Takagi of Sunnyvale CA (US)

Sen Li of Mountain View CA (US)

Ruoyi Jiang of Sunnyvale CA (US)

Yang Jiao of San Mateo CA (US)

Yang Zhang of Sunnyvale CA (US)

Zhuo Zhang of Santa Clara CA (US)

CONTRIBUTION INCREMENTALITY MACHINE LEARNING MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18625830 titled 'CONTRIBUTION INCREMENTALITY MACHINE LEARNING MODELS

The patent application describes methods, systems, and computer programs for training and using machine learning models.

• The model represents relationships between user attributes, content exposures, and performance levels for a target action using organic exposure data and third-party exposure data.
• Incremental performance levels attributable to third-party exposures at the time of the target action are determined using the model.
• Transmission criteria for digital components to which the user was exposed are modified based on the incremental performance.

Potential Applications: This technology could be applied in digital marketing to optimize content exposure and improve user performance levels.

Problems Solved: This technology addresses the challenge of effectively utilizing exposure data to enhance user performance.

Benefits: The technology can lead to more targeted content delivery and improved user engagement.

Commercial Applications: This technology could be valuable for digital advertising agencies looking to enhance the effectiveness of their campaigns.

Prior Art: Researchers interested in this technology may want to explore prior studies on machine learning models in digital marketing.

Frequently Updated Research: Stay updated on advancements in machine learning algorithms and their applications in digital marketing.

Questions about the technology: 1. How does this technology improve user performance levels based on exposure data? 2. What are the potential implications of modifying transmission criteria for digital components based on incremental performance levels?

Original Abstract Submitted

Methods, systems, and computer programs encoded on a computer storage medium, for training and using machine learning models are disclosed. Methods include creating a model that represents relationships between user attributes, content exposures, and performance levels for a target action using organic exposure data specifying one or more organic exposures experienced by a particular user over a specified time prior to performance of a target action by the particular user and third party exposure data specifying third party exposures of a specified type of digital component to the particular user over the specified time period. Using the model, an incremental performance level attributable to each of the third party exposures at an action time when the target action was performed by the particular user is determined. Transmission criteria for at least some digital components to which the particular user was exposed are modified based on the incremental performance.