Notification Service Click-Through Probability Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Social networking systems face challenges in delivering notifications effectively, as existing methods often result in a low click-to-impression ratio and can bother uninterested users, leading to decreased user engagement and increased annoyance.
Innovation Solution
Implementing a notification service that uses machine-learning techniques to dynamically determine whether to deliver notifications to users based on their interest, by calculating a click-through probability and comparing it to a threshold value, ensuring that only interested users receive notifications, thereby improving the average click-to-impression ratio and allowing for higher notification frequency without bothering recipients.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If notifications are sent to all users, then notification delivery frequency increases, but user engagement decreases due to annoyance
Solution Approach 1:
The patent applies local quality by differentiating notification delivery based on individual user characteristics and interests. Instead of uniform notification delivery to all users, the system calculates user-specific click-through probabilities and selectively delivers notifications only to users with high predicted engagement, thereby maintaining high delivery frequency for interested users while avoiding annoyance to uninterested users.
Solution Approach 2:
The system dynamically changes the notification delivery parameter based on calculated click-through probabilities. By continuously updating user interest profiles and recalculating engagement probabilities, the system adapts notification delivery parameters in real-time, sending notifications when probability exceeds thresholds and withholding them when probability is low, thus optimizing both delivery frequency and user experience.
2Quantity of substance
If notifications are sent to all users, then notification volume increases, but click-to-impression ratio decreases
Solution Approach 1:
The system performs preliminary action by calculating click-through probabilities and predicting user engagement before actually delivering notifications. This pre-screening process identifies which users are likely to engage with notifications, allowing the system to send notifications only to pre-identified interested users, thereby maintaining high notification volume while ensuring high click-to-impression ratios.
Solution Approach 2:
The notification service automatically performs user interest assessment and notification filtering without manual intervention. The system self-manages the entire process of calculating probabilities, comparing against thresholds, and making delivery decisions, thereby efficiently optimizing the ratio of notifications sent to notifications clicked while maintaining high overall notification volume.
3Measurement precision
If machine-learning techniques are implemented for recipient targeting, then notification precision improves, but system complexity increases
Solution Approach 1:
The patent introduces an intermediary notification service that sits between the application and the user base. This intermediary service handles the complex machine-learning calculations and decision-making processes, shielding the application from complexity while providing precise recipient targeting. The notification service acts as a mediator that translates user data into delivery decisions, improving precision without burdening the application with complex algorithms.
Solution Approach 2:
The system replaces manual or rule-based notification delivery mechanisms with machine-learning-based automated decision-making. By substituting complex mechanical or manual processes with intelligent algorithms that automatically calculate click-through probabilities and make delivery decisions, the system achieves high precision in recipient targeting while managing complexity through automation rather than manual processes.
Data Source
AI summary
A method may include one or more computing devices receiving an indication that a triggering action has been detected from a client device, identifying one or more notifications associated with the triggering action, wherein the one or more notifications have been stored in a queue prior to receiving the indication that the triggering action has been detected, and, for each of the one or more identified notifications, calculating a click-through probability that a user associated with the client device will interact with the notification, wherein the click-through probability is calculated based at least in part on a period the notification was stored in the queue prior to receiving the indication that the of the triggering action has been detected, and determining whether the calculated click-through probability satisfies a threshold and sending, in response to determining that the calculated click-through probability satisfies the threshold, the identified notification to the client device.