Closed-Form Contact Center Prediction Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current contact center prediction models are computationally slow, difficult to use, and limited in capability, particularly failing to accurately predict long-term behavior and react to systemic changes due to assumptions about customer patience and communication patterns.
Innovation Solution
A closed-form simulation modeling system that analyzes historical Automatic Call Distribution data to build and validate models, predicting contact center behavior without pre-running simulations, and incorporating customer patience profiles to estimate key performance metrics like service level, average speed of answer, and abandon rate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If discrete event simulation modeling is used to predict contact center behavior, then accuracy in capturing complex customer patience profiles is improved, but computational speed and ease of use deteriorate
Solution Approach 1:
The patent replaces complex discrete event simulation modeling with a closed-form mathematical model. This substitution eliminates the need for computationally intensive simulations while maintaining the ability to accurately predict contact center behavior by using analytical solutions based on probability theory and queuing models.
Solution Approach 2:
The patent transforms the modeling approach by changing from a simulation-based parameter set to a closed-form mathematical parameter set. The closed-form model uses analytical expressions with parameters such as arrival rates, service rates, and patience thresholds, which can be directly calculated without running simulations, thus improving computational speed while preserving prediction accuracy.
2Measurement precision
If discrete event simulation modeling is used to predict contact center behavior, then accuracy in capturing complex customer patience profiles is improved, but ease of operation deteriorates
Solution Approach 1:
The patent replaces complex discrete event simulation modeling with a closed-form mathematical model. This substitution eliminates the need for computationally intensive simulations while maintaining the ability to accurately predict contact center behavior by using analytical solutions based on probability theory and queuing models.
3Productivity
If closed form simulation modeling is used instead of discrete event simulation, then computational speed and ease of use are improved, but the ability to handle complex customer patience profiles may deteriorate
Solution Approach 1:
The patent transforms the modeling approach by changing from a simulation-based parameter set to a closed-form mathematical parameter set. The closed-form model uses analytical expressions with parameters such as arrival rates, service rates, and patience thresholds, which can be directly calculated without running simulations, thus improving computational speed while preserving prediction accuracy.
4Device complexity
If traditional prediction models with assumptions about customer patience are used, then model simplicity is improved, but ability to react to systemic changes deteriorates
Solution Approach 1:
The patent introduces dynamic elements into the closed-form model by allowing parameters such as arrival rates, service rates, and patience thresholds to change over time based on observed patterns in the data. This enables the model to adapt to systemic changes in contact center behavior while maintaining its mathematical tractability and relative simplicity.
Data Source
AI summary
A system and method are presented for predicting contact center behavior. In one embodiment, closed form simulation modeling may be used to simulate behavior from input distributions. Models may be created through staging and analysis of historical Automatic Call Distribution data. Service level, average speed of answer, abandon rate, and other data may be predicted to generate forecasts and analysis of contact center behavior. Examples of behavior may include staffing levels, workload, and the Key Performance Index of metrics such as service level percentage, average speed of answer, and abandonment rate percentage.