Predictive Profile Update via Usage Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing authentication platforms face inefficiencies in updating account profiles, leading to inaccuracies and significant computing resources being required, as they often rely on sequential updates that can cause stale data issues, especially with a large number of accounts and global transaction processing.
Innovation Solution
A system that predicts the likelihood of account profile usage and ranks accounts based on this likelihood, allowing for efficient updating of the most critical profiles first, using a prediction engine with machine learning models like recurrent neural networks to prioritize updates, thereby ensuring current data is available for access requests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sequential updating of all account profiles is performed, then completeness of profile updates is improved, but time required and computing resources increase significantly
Solution Approach 1:
The patent divides the account profile update process into segments based on predicted usage likelihood. Instead of updating all profiles sequentially in a single batch, the system segments profiles into multiple groups (e.g., high-usage, medium-usage, low-usage) and updates them in parallel or in prioritized batches. This segmentation reduces the time required while maintaining completeness by ensuring all segments are eventually updated.
Solution Approach 2:
The system performs preliminary actions by predicting which account profiles are most likely to be used before the update process begins. Based on these predictions, the system prioritizes and pre-schedules updates for high-likelihood profiles, ensuring they are updated first. This preliminary ranking and prioritization reduces overall update time by focusing resources on the most critical profiles while still completing updates for all accounts.
2Device complexity
If sequential updating based on numerical index is used, then simplicity of update process is improved, but data accuracy deteriorates due to stale information
Solution Approach 1:
Before executing the update process, the system performs a preliminary prediction of account profile usage likelihood. This preliminary action enables the system to rank and prioritize profiles before updating, ensuring that high-usage profiles are updated first with the most current data. This maintains data accuracy without significantly increasing process complexity, as the prediction step is integrated into the existing update workflow.
3Ease of operation
If all account profiles are updated with equal priority, then fairness of update distribution is improved, but efficiency deteriorates due to lack of prioritization
Solution Approach 1:
The patent applies local quality by assigning different priorities to different account profiles based on their individual usage likelihoods. Instead of treating all profiles uniformly, the system evaluates each profile's specific characteristics and predicts its usage probability, then updates profiles with higher predicted usage first. This differentiated approach improves efficiency by focusing resources where they are most needed while maintaining a form of fairness through systematic prioritization based on actual usage patterns.
Solution Approach 2:
The system performs preliminary prediction and ranking of account profiles before the update process. This preliminary action establishes a prioritization scheme that guides the update sequence, ensuring efficient resource allocation. Profiles are ranked based on predicted usage likelihood, and updates are executed in this prioritized order, improving overall productivity while maintaining operational simplicity through automated ranking.
4Loss of time
If profile updates are performed during peak transaction periods, then timeliness of data availability is improved, but system performance deteriorates due to resource constraints
Solution Approach 1:
The system performs preliminary prediction of account profile usage likelihood and prioritizes updates accordingly. By identifying and ranking high-usage profiles before the update process, the system can focus computational resources on the most critical profiles during peak periods. This ensures timely data availability for the most important accounts while maintaining system performance by avoiding attempts to update all profiles simultaneously with equal priority.
Solution Approach 2:
The update process is segmented into priority-based batches, with high-usage profiles updated first during peak transaction periods. This segmentation allows the system to maintain reliability by updating critical profiles even under resource constraints, while lower-priority profiles are updated in subsequent batches when resources become available. This approach balances timeliness for critical accounts with overall system performance.
Data Source
AI summary
Methods and systems are provided to efficiently update account profiles based on a predicted likelihood of use, including by ranking the account profiles according to the likelihood of use. The disclosed system can considerably improve the processing time to update account profiles with the most recent information available, including new access requests. An authentication platform receives a plurality of new access requests, including request data and account identifiers associated with account profiles. The request data is transmitted to a prediction engine that determines a ranking of the account identifiers based on a predicted likelihood of use during a next time interval. A profile batch scheduler retrieves a first set of access requests based on the ranking. The system updates a first set of account profiles based on the ranking, and stores the updated account profiles for use by the authentication platform.