Segment Size Estimation Using User Interaction Subsets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional user prediction systems fail to accurately estimate the size of future user segments based on historical data, leading to inefficient targeting of content and resource allocation.
Innovation Solution
A segment size estimation system that uses historical time series data to identify user segments and subdivisions, computing separate predictions for each subset of users based on their engagement levels, and providing customized content to users predicted to interact with the content channel in the future.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional user prediction systems use simple segment-based prediction, then the prediction process is simple and fast, but the prediction accuracy is low
Solution Approach 1:
The patent divides the user segment into two distinct subsets: active users (those who interacted with the content channel in the reference time period) and inactive users (those who did not interact). By computing separate return values for each subset and combining them, the system achieves more accurate predictions while maintaining a relatively simple overall structure. This segmentation allows the system to capture different behavioral patterns without requiring a completely complex predictive model.
2Measurement precision
If the system segments users into subsets for separate prediction, then prediction accuracy improves, but computational complexity increases
Solution Approach 1:
The system segments users based on their interaction history into active and inactive subsets, computing return values separately for each. This segmentation improves prediction accuracy by accounting for different user behaviors while keeping computational requirements manageable through simple counting and arithmetic operations.
Solution Approach 2:
The patent changes the parameter of user classification from a single uniform segment to two distinct segments based on interaction frequency. This parameter change enables more accurate predictions by capturing the difference between active and inactive users, while the computational overhead remains relatively low since it only requires checking interaction counts and performing basic arithmetic.
Data Source
AI summary
One aspect of systems and methods for segment size estimation includes identifying a segment of users for a first time period based on time series data, wherein the time series data includes a series of interactions between users and a content channel and wherein the segment includes a portion of the users interacting with the content channel during the first time period; computing a segment return value for a second time period based on the time series data by computing a first subset and a second subset of the segment, wherein the first subset includes users that interact with the content channel greater than a threshold number of times during a range of the time series data and the second subset comprises a complement of the first subset with respect to the segment; and providing customized content to a user in the segment based on the segment return value.