Google llc (20240232936). MODEL ORCHESTRATOR simplified abstract
Contents
MODEL ORCHESTRATOR
Organization Name
Inventor(s)
Francesco Nerieri of San Francisco CA (US)
Di-Fa Chang of Cupertino CA (US)
Lan Huang of Menlo Park CA (US)
Xinlong Bao of Los Altos CA (US)
MODEL ORCHESTRATOR - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240232936 titled 'MODEL ORCHESTRATOR
The abstract describes methods, systems, and apparatus for determining attributions for unattributed outcomes across different content channels. The process involves receiving outcome data representing unattributed outcomes, receiving attribution data representing modeled attributions, updating measures based on criteria, and determining updated attributions.
- The innovation involves a model orchestrator receiving outcome and attribution data to determine attributions for unattributed outcomes.
- The method updates measures based on criteria to determine new attributions for outcomes to exposures.
- The system includes a plurality of outcome models to model attributions for unattributed outcomes.
- Computer programs encoded on a computer storage medium facilitate the process of determining attributions for unattributed outcomes.
- The process helps in understanding the impact of exposures on outcomes across different content channels.
Potential Applications: This technology can be applied in digital marketing to optimize advertising strategies and budget allocation based on attributions for unattributed outcomes.
Problems Solved: This technology addresses the challenge of determining attributions for unattributed outcomes, providing insights into the effectiveness of different exposures.
Benefits: The technology helps in improving decision-making processes related to advertising and content distribution by providing accurate attributions for unattributed outcomes.
Commercial Applications: Optimizing digital marketing campaigns, improving ROI on advertising spend, and enhancing content distribution strategies are potential commercial applications of this technology.
Questions about the technology: 1. How does this technology improve attribution modeling for unattributed outcomes? 2. What are the key criteria used to update measures and determine updated attributions in this process?
Original Abstract Submitted
methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining attributions for unattributed outcomes across different content channels. the method includes receiving, by a model orchestrator, outcome data representing a set of unattributed outcomes, where each unattributed outcome does not have an observed attribution to an exposure of a set of predetermined exposures. the attribution data representing a set of modeled attributions from each outcome model of a plurality of outcome models are received by the model orchestrator, where each set of modeled attribution includes a respective measure between one or more unattributed outcomes and one or more exposures. the respective measures are updated based on one or more criteria for determining one or more updated attributions, where each updated attribution indicates a new attribution of a respective outcome from the set of unattributed outcomes to a corresponding exposure of the set of predetermined exposures.
