Predictive Data Analysis Using Value-Based Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Predictive data analysis in transactional domains such as financial and healthcare faces challenges due to large amounts of complex data and the difficulty in integrating value-based predictive inputs into conventional techniques, leading to inefficiencies and unreliable results.
Innovation Solution
The method involves generating entity-level predictive inputs based on value-based information, using quantile regression distributions to identify non-outlier portions and scaling quantile regression values, which enables more accurate and reliable predictive data analysis by reducing data size and dimensionality, and effectively integrating value-based predictive inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If conventional predictive data analysis techniques are used on large amounts of complex transactional data, then comprehensive analysis coverage is achieved, but processing efficiency and reliability deteriorate
Solution Approach 1:
The patent segments the large complex dataset into entity-level units (e.g., customer-level data) and processes them independently through parallel computing operations. This segmentation allows the system to handle comprehensive data volumes while maintaining processing efficiency by dividing the analytical workload into manageable, concurrently executable tasks across multiple computing nodes.
2Quantity of substance
If conventional predictive data analysis techniques are used on complex transactional data, then comprehensive analysis coverage is achieved, but analysis reliability deteriorates
Solution Approach 1:
The patent transforms the complex transactional data into standardized entity-level predictive inputs by changing the data representation parameters. Each entity is characterized by a consistent set of attributes (e.g., customer ID, value-based metrics, behavioral features) that normalize the variability in raw transactional data. This parameter standardization improves analysis reliability by ensuring consistent processing of complex data across different entities and time periods.
3Measurement precision
If value-based predictive inputs are integrated into conventional techniques, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
The patent introduces value-based predictive inputs as intermediary variables that mediate between raw transactional data and final predictions. These intermediaries (e.g., customer lifetime value, predicted response probability) capture essential predictive information in a standardized form that can be integrated into existing analytical models without requiring fundamental redesign of the system architecture, thus improving accuracy while limiting complexity increases.
4Productivity
If entity-level predictive inputs are used, then processing efficiency improves, but data dimensionality increases
Solution Approach 1:
The patent extracts only the essential predictive features from the full entity-level data structure, taking out the most relevant attributes (e.g., value-based metrics, key behavioral indicators) while discarding redundant information. This extraction process maintains processing efficiency by focusing computational resources on critical features while reducing the effective dimensionality of the data fed into predictive models through selective feature extraction.
Data Source
AI summary
There is a need for solutions that perform predictive data analysis using a value-based predictive input. This need can be addressed by, for example, determining, based at least in part on the value-based predictive input, a plurality of predictive component values; for each predictive component value of the plurality of predictive component values: obtaining a quantile regression distribution for the predictive component value; determining, based at least in part on the quantile regression distribution, a non-outlier portion of the quantile regression distribution; generating, for each quantile regression value of the one or more quantile regression values that is associated with the non-outlier portion, a scaled quantile regression value; and determining, based at least in part on each scaled quantile regression value for a quantile regression value associated with a predictive component value of the plurality of predictive component values, an entity opportunity prediction of the one or more entity predictions for the prediction entity.