Automated GUI Selection via Lookalike Cohort Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Implementing improvements to software applications, such as enhancing graphical user interfaces (GUIs), is a time-consuming, expensive, and unpredictable process, particularly when trying to automatically select the most effective GUI for deployment.
Innovation Solution
A computer-implemented method that tracks data on a new population of software application users, generates a distribution by mapping this data to lookalike cohorts, uses a random sampling algorithm to extract samples, and then selects a GUI based on predicted long-term values and their estimated distributions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual methods are used to select and implement GUI improvements, then the selection process can be thorough and consider multiple factors, but the process becomes time-consuming, expensive, and unpredictable
Solution Approach 1:
The patent replaces manual mechanical evaluation processes with automated computational systems. Machine learning models and algorithms automatically analyze user interaction data, predict long-term values, and select optimal GUI improvements, eliminating the time-consuming manual review process while maintaining or improving selection accuracy through data-driven insights
Solution Approach 2:
The system creates synthetic copies of user populations through lookalike cohorts that replicate the characteristics and behaviors of actual users. These synthetic cohorts allow rapid testing and evaluation of multiple GUI variations simultaneously, enabling parallel processing of improvement options without requiring extensive real-user testing for each variant
2Adaptability or versatility
If multiple different sets of GUIs are proposed to improve utility, then more improvement options are available, but the complexity of selecting the best option increases
Solution Approach 1:
The system evaluates multiple GUI improvement options by changing and comparing key performance parameters such as predicted long-term user value, engagement metrics, and conversion rates. By standardizing evaluation on these quantifiable parameters, the system can objectively compare diverse GUI proposals and automatically select the optimal option based on data-driven metrics rather than subjective assessment
Solution Approach 2:
The patent introduces an intermediary computational layer that includes machine learning models and prediction algorithms. This intermediary automatically processes and evaluates multiple GUI proposals, translating diverse design options into comparable performance predictions. The intermediary system handles the complexity of comparing multiple options, presenting simplified recommendations to decision-makers
3Measurement precision
If extensive user data is collected and analyzed to ensure accurate prediction of long-term values, then prediction accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The system extracts and focuses on the most critical features and signals from extensive user data that have the highest predictive value for long-term outcomes. By identifying and prioritizing key data elements rather than processing all available data equally, the system maintains high prediction accuracy while reducing computational burden and processing time through targeted analysis of the most informative data points
Data Source
AI summary
A computer-implemented method including tracking data describing a new population of users of a software application including different graphical user interfaces (GUIs). The method also includes generating a distribution by mapping the data to lookalike cohorts. The method also includes extracting, using a random sampling algorithm, samples from the distribution. The method also includes generating, from the samples, a normal distribution of predicted long term values of the new population of users. The method also includes selecting an expected long term value from the normal distribution. The method also includes generating, from the normal distribution, an estimated distribution, around the expected long term value, of estimated long-term values for the new population. The method also includes selecting, using the expected long term value and the estimated distribution, a selected GUI from among the different GUIs. The method also includes modifying the software application by presenting the selected GUI.