17927398. MACHINE LEARNING RANK AND PREDICTION CALIBRATION simplified abstract (GOOGLE LLC)
Contents
MACHINE LEARNING RANK AND PREDICTION CALIBRATION
Organization Name
Inventor(s)
Gil Shamir of Sewickley PA (US)
Zhuoshu Li of Pittsburgh PA (US)
MACHINE LEARNING RANK AND PREDICTION CALIBRATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17927398 titled 'MACHINE LEARNING RANK AND PREDICTION CALIBRATION
The patent application describes methods, systems, and apparatus for training and using machine learning models to provide recommendations for digital components based on engagement predictions and rankings.
- Receiving a digital component request
- Using a first ML model to output scores indicating the likelihood of a positive outcome for digital components
- Providing input data to a second ML model, including feature values for selected digital components based on output scores
- Training the second ML model to output engagement predictions and rankings of digital components
- Producing a second output that includes rankings and engagement predictions for the subset of digital components
- Providing at least one digital component based on the second output
Potential Applications: - Personalized content recommendations - Targeted advertising strategies - E-commerce product recommendations
Problems Solved: - Improving user engagement with digital content - Enhancing the effectiveness of marketing campaigns - Increasing conversion rates for online businesses
Benefits: - Enhanced user experience - Higher engagement rates - Improved ROI for marketing efforts
Commercial Applications: - Digital marketing agencies - E-commerce platforms - Content recommendation services
Questions about the technology: 1. How does this technology improve upon traditional recommendation systems? 2. What data sources are typically used to train the machine learning models in this system?
Frequently Updated Research: - Stay up to date with advancements in machine learning algorithms for content recommendation systems.
Original Abstract Submitted
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for training and using machine learning (ML) models. In one aspect, a method includes receiving a digital component request. A first ML model can output scores indicating a likelihood of a positive outcome for digital components. Input data can be provided to a second ML model and can include feature values for a subset of digital components that were selected based on the output scores. The second ML model can be trained to output an engagement predictions and/or ranking of digital components based at least in part on feature values of digital components that will be provided together as recommendations, and can produce a second output that includes ranking and engagement predictions of the digital components in the subset of digital components. At least one digital component can be provided based on the second output.
