Send Time Optimization for Electronic Communications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for sending electronic communications, such as emails and text messages, do not optimize the time of delivery to maximize the likelihood of recipients reading the messages, as they are typically sent at convenient times for the sender rather than considering the recipients' preferences.
Innovation Solution
A system that learns send time preferences by analyzing previous communication data to construct response models for each contact, using day-hour combinations to determine the best time to send messages, employing Thompson sampling for adaptive online experimentation and Beta-distributed random variables to estimate response rates, thereby optimizing send times for higher engagement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If messages are sent at convenient times for the sender (e.g., just after composition or in batches), then the ease of operation for the sender is improved, but the likelihood of recipients reading the communication deteriorates
Solution Approach 1:
The system changes the time parameter of message delivery from sender-convenient times to recipient-optimal times determined by response models. It analyzes historical open events to identify patterns in recipient behavior and selects send times that maximize the probability of recipients being active and engaged, thereby improving reading likelihood without requiring manual intervention for each message timing decision.
2Reliability
If send times are optimized for each recipient based on historical data, then the likelihood of recipients opening communications is improved, but the device complexity increases
Solution Approach 1:
The system implements self-service by automatically building and updating response models for each contact based on their historical open events. The models autonomously learn recipient preferences and generate optimized send time recommendations without requiring manual configuration or intervention. This automation reduces the operational complexity despite the sophisticated personalization being applied.
Solution Approach 2:
The system employs feedback mechanisms by continuously monitoring open events and using this data to refine response models. The models are updated with new open event data, allowing the system to adapt to changing recipient behaviors and improve send time predictions over time, thereby maintaining high effectiveness while managing complexity through data-driven optimization.
Data Source
AI summary
Disclosed are systems and methods for determining the best time to send an electronic communication from a sender to a recipient. In one aspect, a method is disclosed that includes selecting a time window from a series of candidate time windows based on a corresponding first value for each candidate time window, wherein each first value is representative of a likelihood of receiving an event notification within a specified first delay after the candidate time window. The method further includes selecting a time period from a plurality of time periods within the selected time window based on a corresponding second value for each time period representative of the likelihood of receiving the event notification within a specified second delay after the time period. The method further includes generating a signal indicative of a time within the selected time period at which an electronic communication should be sent.