Selecting an algorithm for identifying similar user identifiers based on predicted click-through-rate
Topics: Personalization, User Signals
This Google patent describes a computerized method for selecting the most effective algorithm to identify similar user identifiers based on predicted click-through rates. The system compares different algorithms by generating models that identify similar users, calculating predicted click-through rates for these user groups, and determining weighted averages to evaluate which algorithm performs better at identifying valuable similar users. This approach allows for faster and more accurate evaluation compared to using actual click-through rates, as it doesn’t require waiting for real user interactions.