Doordash, inc. (20240249314). MACHINE LEARNING WITH DATA SYNTHESIZATION simplified abstract

MACHINE LEARNING WITH DATA SYNTHESIZATION

Organization Name

doordash, inc.

Inventor(s)

Robert Bryant Kaspar of Berkeley CA (US)

Alok Gupta of San Francisco CA (US)

Aman Dhesi of San Francisco CA (US)

MACHINE LEARNING WITH DATA SYNTHESIZATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240249314 titled 'MACHINE LEARNING WITH DATA SYNTHESIZATION

The patent application describes a system where a computing device collects data from multiple sources related to user interactions with information provided by service providers. The device then determines if the users are new or existing based on user information data. Machine learning models are used to assign values to new users and adjust the received data accordingly. Synthetic data is generated using machine learning models, and resource allocation is determined by comparing the adjusted and synthetic data from different sources.

• Computing device collects data from various sources on user interactions with service providers.
• Determines if users are new or existing based on user information data.
• Uses machine learning models to assign values to new users and adjust data.
• Generates synthetic data using machine learning models.
• Determines resource allocation by comparing adjusted and synthetic data from different sources.

1. 1. 1. Potential Applications:

This technology can be applied in various industries such as marketing, e-commerce, and customer relationship management systems to optimize resource allocation and improve user engagement.

1. 1. 1. Problems Solved:

This technology addresses the challenges of accurately identifying new and existing users, optimizing resource allocation, and enhancing user experience based on data-driven insights.

1. 1. 1. Benefits:

- Improved user engagement and personalized experiences. - Efficient resource allocation leading to cost savings. - Enhanced decision-making based on accurate user data.

1. 1. 1. Commercial Applications:

This technology can be utilized in marketing automation platforms, customer analytics tools, and online advertising systems to enhance user targeting and optimize marketing strategies.

1. 1. 1. Questions about the Technology:
         1. 1. How does this technology improve user engagement?

This technology enhances user engagement by accurately identifying new and existing users and providing personalized experiences based on data insights.

1. 1. 1. 1. 2. What are the potential cost-saving benefits of using this technology?

By optimizing resource allocation and improving decision-making, this technology can lead to cost savings in various industries.

Original Abstract Submitted

in some examples, a computing device receives, from a plurality of data sources associated with a plurality of service providers, data related to user interactions with information provided by the service providers. the computing device determines users associated with the user interactions, and determines whether the users are new users or existing users based at least on accessing a user information data structure. the computing device uses a value-determining machine learning model to determine respective values associated with the new users, and adjusts values of the received data based on the respective values. the computing device uses a plurality of data synthetization machine learning models to generate synthetic data based on the adjusted data. the computing device determines an allocation of resources at least by comparing the adjusted data and the synthetic data of the data sources with the adjusted data and synthetic data of others of the data sources.