DoorDash has filed a patent for a system that uses data synthetization machine learning models to generate synthetic data. The system receives data from multiple groups of data sources and generates synthetic data based on this input. It then determines the allocation of resources based on a comparison between the original data and the synthetic data. GlobalData’s report on DoorDash gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on DoorDash, supply chain management systems was a key innovation area identified from patents. DoorDash's grant share as of September 2023 was 77%. Grant share is based on the ratio of number of grants to total number of patents.

Data synthesis and resource allocation system using machine learning

Source: United States Patent and Trademark Office (USPTO). Credit: DoorDash Inc

How well do you really know your competitors?

Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.

Company Profile – free sample

Thank you!

Your download email will arrive shortly

Not ready to buy yet? Download a free sample

We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form

By GlobalData

A recently filed patent (Publication Number: US20230289847A1) describes a system and method for resource allocation based on synthetic data generation and comparison. The system includes one or more processors that receive data from multiple groups of data sources. The processors access data synthesis machine learning models corresponding to each group of data sources and generate synthetic data based on the received data. The system then determines the allocation of resources by comparing the original data with the synthetic data.

In addition to generating synthetic data, the system also creates graphs based on the original data and synthetic data. These graphs are used to further determine the allocation of resources by comparing the slopes of the curves in the graphs. The first curve is based on the original data and synthetic data from the first group of data sources, while the second curve is based on the original data and synthetic data from the second group of data sources.

The system also includes a training process for the data synthesis machine learning models. The received data is used to train the models, with each model corresponding to a specific group of data sources. The system creates a training data set from a portion of the received data and validation data sets for each group of data sources. The validation data sets are used to validate the performance of the data synthesis machine learning models and determine the optimal amount of synthetic data to produce for each individual data source within the groups.

The method described in the patent involves similar steps as the system, including receiving data from multiple groups of data sources, generating synthetic data using data synthesis machine learning models, and determining resource allocation based on the comparison of original data and synthetic data. The method also includes creating graphs and comparing the slopes of the curves in the graphs to determine resource allocation.

Overall, this patent presents a system and method for resource allocation based on synthetic data generation and comparison. By utilizing data synthesis machine learning models and graph analysis, the system and method aim to optimize resource allocation based on the characteristics of the original data and the synthetic data.

To know more about GlobalData’s detailed insights on DoorDash, buy the report here.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.