Dynamic Outlier Bias Reduction in Facility Operating Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for removing outlier data in statistical and mathematical model development are subjective and prone to introducing bias, lacking an objective, data-driven approach for ensuring data quality and validation, particularly in complex analyses involving greenhouse gas emissions and other environmental metrics.
Innovation Solution
A computer-implemented method and system that dynamically identifies and reduces outlier bias through iterative processes, using error threshold values and optimization models to generate new model coefficients, ensuring that only data within specified error criteria is included in calculations, thereby improving the accuracy and fairness of statistical and mathematical models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If outlier data is removed using subjective processes, then data quality can be improved, but the process introduces bias and lacks objectivity
Solution Approach 1:
The patent replaces the manual, subjective mechanical process of outlier identification with an automated computational system. The system uses algorithms to objectively identify outliers based on statistical criteria, eliminating human subjectivity while maintaining data quality improvements.
Solution Approach 2:
The patent transforms the outlier identification process by changing from subjective judgment parameters to objective statistical parameters. It uses quantifiable metrics such as standard deviations, percentiles, and statistical thresholds to define outliers, replacing subjective assessments with measurable, reproducible criteria.
2Measurement precision
If iterative optimization is performed to reduce outlier bias, then model accuracy is improved, but computational time and complexity increase
Solution Approach 1:
The patent performs preliminary actions by pre-defining statistical criteria and thresholds for outlier identification before the main optimization process. This preparation work includes establishing confidence levels, standard deviation multiples, and percentile thresholds that guide the iterative process, reducing computational burden during execution.
Solution Approach 2:
The patent applies partial action by selectively removing only the most significant outliers based on statistical thresholds, rather than attempting to remove all potential outliers. This approach achieves sufficient model accuracy improvement without the excessive computational cost of examining every data point in depth.
Data Source
AI summary
In at least one embodiment, the present description is directed to a computer system, having a processor to at least: electronically receive a model for one or more operating conditions, and facility operating data; iteratively perform one or more iterations of outlier bias reduction in the facility operating data based on the model, including: determining model predicted values, comparing the model predicted values to the facility operating data, removing bias facility operating data from the facility operating data of the plurality of facilities, and constructing, based at least in part on the non-biased facility operating a data, an updated model with one or more updated coefficients; determine, based on non-biased facility operating data, a non-biased performance standard for the one or more operating conditions; and track, based on the no-biased performance standard and the facility operating data, operating performance of each respective facility of the plurality of facilities.