Order Turnaround Time Prediction Using Statistical Distributions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information verification systems rely on constant turnaround time (TAT) values for predicting order completion, which fail to accurately reflect the varying factors influencing individual verification services, leading to discrepancies in actual order completion times.
Innovation Solution
The method employs statistical distribution functions for each elementary verification service, continuously updated with historical data, to predict order turnaround time by determining the types and locations of services and content providers, using a predictive model to calculate mean values, median values, and confidence intervals before processing, and an apparatus to maintain and update these distributions for accurate results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If constant TAT values are used for predicting order completion, then the prediction system is simple to operate, but the accuracy of TAT evaluation deteriorates
Solution Approach 1:
The patent changes the parameter representation from constant TAT values to statistical distribution functions that capture the variability and uncertainty of turnaround times. Each elementary verification service is associated with a statistical distribution function that models its TAT characteristics, allowing the system to provide accurate predictions while maintaining operational simplicity through automated statistical calculations.
2Measurement precision
If statistical distribution functions are used for each elementary verification service, then the accuracy of TAT evaluation is improved, but the device complexity increases
Solution Approach 1:
The patent segments the verification system into elementary verification services, each with its own statistical distribution function. This segmentation allows the complex system to be broken down into manageable components, where each service can be independently modeled and updated with historical data, reducing overall system complexity while improving prediction accuracy.
Solution Approach 2:
The system implements self-service through automated collection and processing of historical data to continuously update statistical distribution functions. The apparatus automatically maintains and updates these functions without requiring manual intervention, reducing operational complexity while ensuring accurate, up-to-date predictions.
3Reliability
If historical data is continuously used to update statistical distribution functions, then the reliability of predictions is improved, but the loss of time for data processing increases
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing statistical distribution functions based on historical data before they are needed for predictions. The system continuously updates these functions in the background using accumulated historical data, so that when prediction is needed, the calculations are already prepared and can be quickly applied to current orders without causing delays.
Data Source
AI summary
A method and apparatus for the prediction of order turnaround time in an information verification system is disclosed. An information verification order comprises several and diverse instances of different types of elementary verification/validation/search services. Each of these services is characterized by its own turnaround time (TAT) statistical distribution function which is used in the prediction of order turnaround time. A Monte Carlo algorithm is used to determine the order turnaround time.