Predictive Data Feature Target Zones for Process Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to identify specific factors contributing to outcome scores associated with processes, such as customer satisfaction in insurance claim processing, and unclear which values of these factors impact satisfaction levels.
Innovation Solution
A computer-implemented method using a machine learning model trained on data from various sources to identify predictive data features and determine target zones indicating values likely to be associated with desired outcome scores, incorporating operational, customer, and worker data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a machine learning model is trained on multiple data sources to identify predictive data features, then the accuracy of identifying factors influencing outcome scores is improved, but the complexity of the system increases
Solution Approach 1:
The system segments the complex task of identifying predictive factors by training the machine learning model on multiple separate data sources (operational data, customer data, worker data) independently, then integrating the results. This allows the system to maintain high accuracy while managing complexity through modular data processing.
Solution Approach 2:
The patent introduces an intermediary machine learning model that acts as a mediator between raw multi-source data and the final identification of predictive data features. This intermediary model simplifies the overall system architecture by centralizing the complex analysis function in a trained model rather than requiring complex real-time processing across multiple systems.
2Productivity
If target zones are determined for predictive data features to indicate values associated with desired outcome scores, then the ability to optimize process performance is improved, but the difficulty of detecting and measuring increases
Solution Approach 1:
The system performs preliminary action by determining target zones for predictive data features before actual process optimization occurs. The machine learning model is trained in advance to identify these target zones, allowing the system to provide guidance on optimal values for operational, customer, and worker data before processes are executed, thereby simplifying real-time measurement and decision-making.
3Reliability
If data from multiple disparate sources is integrated to train the machine learning model, then the comprehensiveness of predictive analysis is improved, but the loss of time for data processing increases
Solution Approach 1:
The patent applies preliminary action by integrating and processing data from multiple disparate sources (operational data, customer data, worker data) in advance during the model training phase. This allows the comprehensive predictive analysis to be prepared beforehand, so that when the model is deployed, it can quickly provide predictions without requiring real-time integration of all data sources, thereby reducing processing time during actual use.
Data Source
AI summary
Training of a machine learning model can indicate data features within operational data, customer data, and/or worker data that are most predictive of outcome scores, such as customer satisfaction scores, associated with performance of instances of a process by an entity. The training of the machine learning model can also indicate target zones, associated with values of the identified predictive data features, that are associated with outcome scores within a target range. Process data, associated with a set of instances of the process, can be analyzed to identify instances of the process that associated with values of the predictive data features that are, or are not, within the target zones.