Contact Center Staffing Planning Using ML Demand Forecasts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately predicting and precisely applying customer contact volume and duration at an enterprise level contact center for effective staffing remains a challenge.
Innovation Solution
A machine learning model is used to predict contact volume and duration, combined with a planning application that computes a staffing plan minimizing the difference between predicted customer contact time units and staff member availability, utilizing mixed integer linear programming for optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional forecasting methods are used to estimate contact volume, then the process is simpler, but the prediction accuracy and precision are insufficient
Solution Approach 1:
The patent replaces traditional mechanical forecasting methods with machine learning models that use historical contact data, staff performance metrics, and external factors to predict contact volume and duration. This substitution enables more accurate predictions by capturing complex patterns and relationships that traditional methods cannot detect, directly addressing the need for improved measurement precision.
Solution Approach 2:
The patent introduces an intermediary optimization module that acts as a bridge between predicted contact metrics and staffing decisions. This intermediary computes optimal staffing plans by minimizing the difference between predicted contact time units and available staff capacity, thereby resolving the contradiction by adding a specialized component that enhances accuracy without requiring complete system redesign.
2Productivity
If staffing levels are increased to handle peak contact volumes, then service capacity is improved, but operational costs increase
Solution Approach 1:
The patent implements dynamic staffing optimization by computing staffing plans that adapt to predicted contact volumes and durations. The system determines the minimum number of staff members needed to handle predicted contact time units, allowing staffing levels to flex dynamically based on actual demand forecasts rather than maintaining static overstaffing levels. This resolves the contradiction by aligning productivity with precise resource quantity.
Solution Approach 2:
The patent changes the parameter of staffing allocation from fixed to optimized variable levels. By using the optimization module to compute staffing plans that minimize the difference between predicted contact time units and available staff capacity, the system adjusts staffing parameters to achieve optimal service capacity without excessive resource consumption, directly addressing the productivity-resource quantity tradeoff.
3Manufacturing precision
If detailed forecasting is performed for each time period, then staffing precision is improved, but computational complexity increases
Solution Approach 1:
The patent segments the forecasting and optimization process into distinct time periods, computing staffing plans for each future time period independently. This segmentation allows detailed precision at the hourly or daily level while managing computational complexity by breaking down the overall problem into smaller, more manageable sub-problems. Each segment can be optimized separately using the same methodology without requiring computation of the entire time horizon simultaneously.
Data Source
AI summary
In some aspects, the techniques described herein relate to a method including: predicting, with a machine learning model, a predicted contact volume and a predicted contact duration of customer contacts with a contact center for a future time period; providing input data to a planning application, wherein the input data includes the predicted contact volume, the predicted contact duration, a number of available staff members and a number of available contact time units of each of the number of available staff members; and computing, by the planning application, a staffing plan, wherein the staffing plan minimizes a difference between a total number of predicted customer contact time units and a total number of staff member contact time units for the future time period.