AI Predictive Model Data Enrichment for Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current machine learning methods for predictive models in artificial intelligence face challenges in improving training and performance due to inconsistent and incoherent data, which affects decision-making accuracy.
Innovation Solution
The method involves data enrichment through data cleanup, sampling, and transformation of raw data records using algorithms for data integrity analysis, context mining, and smart-agent technology to create predictive models that generate better business decisions by removing irrelevant data fields and adding new fields that enhance prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data fields with little benefit are retained in raw data records, then data completeness is maintained, but prediction accuracy deteriorates due to noise and irrelevant information
Solution Approach 1:
The patent extracts and removes data fields with little benefit from raw data records through automated field identification and elimination. The system analyzes data fields to determine their predictive value and selectively removes irrelevant fields, thereby improving prediction accuracy while maintaining only the necessary data for model training.
Solution Approach 2:
The patent applies different quality standards to different data fields based on their predictive value. Rather than uniformly treating all data fields, the system identifies and retains only those fields that contribute meaningfully to predictions, applying local quality enhancement to specific high-value fields while eliminating low-value ones.
2Measurement precision
If more data fields are added to enrich data records, then prediction accuracy improves, but data processing complexity increases
Solution Approach 1:
The patent performs preliminary data enrichment by automatically identifying and adding beneficial data fields before the main predictive modeling process. The system pre-processes raw data records by incorporating relevant external data sources and deriving new fields that will be useful for prediction, thereby improving accuracy while managing complexity through advance preparation.
Solution Approach 2:
The patent implements self-service data enrichment where the system automatically identifies which data fields to add or modify based on the predictive model's needs. The automated field identification and elimination processes enable the system to self-optimize its data structure without requiring manual intervention, thereby managing complexity while improving prediction accuracy.
3Measurement precision
If manual data cleaning and enrichment processes are used, then data quality improves, but processing time and resource consumption increase
Solution Approach 1:
The patent implements self-service data cleaning and enrichment where the system automatically performs field identification, elimination, and addition processes. The automated system analyzes data fields, determines their predictive value, and executes appropriate actions without manual intervention, thereby maintaining high data quality while significantly improving processing efficiency and reducing resource consumption.
Solution Approach 2:
The patent changes the parameters of data processing by transitioning from manual to automated field identification and manipulation. The system uses automated algorithms to analyze data field characteristics, determine their predictive value, and execute cleaning or enrichment operations, thereby maintaining data quality while improving processing speed and reducing resource requirements.
Data Source
AI summary
A method of improving the training and performance of predictive models. A first method of operating an artificial intelligence machine produces predictive model language documents describing improved predictive models that generate better business decisions from raw data record inputs. A second method of operating an artificial intelligence machine including processors for predictive model algorithms produces and outputs better business decisions from raw data record inputs. Both methods enrich the raw data records their processors are fed by deleting data fields with data values that have little benefit in decision making, and that derive and add new data fields from information sources then available that do benefit in the decision making of the artificial intelligence machine through improved accuracies of prediction.