Working-Shift Staffing With Predictive Adherence Shrinkage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Workforce Management (WFM) systems lack a proactive solution to optimize staffing plans by predicting adherence parameters, leading to high Average Speed of Answer (ASA) and poor customer experience due to manual shrinkage calculations that do not consider adherence factors, resulting in errors and low accuracy.
Innovation Solution
A computerized method that includes configuring a User Interface (UI) to receive date range, Scheduling Unit (SU), and activity code, using forecast adherence, coaching, and time-off engines to calculate shrinkage parameters, automating staffing schedules to maximize adherence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual shrinkage parameter entry is used for multiple Scheduling Units, then staffing plans can be generated, but the process becomes exhaustive and error-prone with low accuracy
Solution Approach 1:
The system automatically calculates shrinkage parameters using adherence data from historical records and machine learning models, eliminating the need for manual entry. The system serves itself by gathering data, processing it through algorithms, and generating staffing plans with accurate shrinkage parameters without human intervention
Solution Approach 2:
The manual mechanical process of entering shrinkage parameters is replaced with an automated computational system that uses machine learning models and adherence data to calculate parameters automatically, substituting human labor with intelligent algorithms
2Reliability
If adherence calculation is performed only in real-time or after activity completion, then agent performance can be tracked, but high Average Speed of Answer and poor customer experience result
Solution Approach 1:
The system performs adherence prediction in advance before the working shift begins, using historical data and machine learning models to forecast adherence parameters. This preliminary action allows staffing schedules to be optimized beforehand, preventing high wait times and poor customer experience
Solution Approach 2:
The system uses historical adherence data as feedback to continuously improve prediction accuracy. By analyzing past adherence patterns and feeding this information back into the machine learning models, the system refines its predictions to better anticipate future adherence behavior
3Ease of manufacture
If shrinkage parameter considers only absence and training but not adherence factor, then staffing calculations can be completed, but accuracy and optimization are reduced
Solution Approach 1:
The shrinkage parameter calculation system integrates multiple factors including absence, training, and adherence into a unified multi-functional parameter. This universal approach allows the system to consider diverse elements that affect agent availability, improving the comprehensiveness and accuracy of staffing calculations
Data Source
AI summary
A computerized-method for optimizing staffing of working-shifts during a date-range by predicting adherence parameter of the working-shift based on an SU. The computerized-method includes: (i) configuring, a UI of a WFM application, to receive: a. date-range; b. SU; and c. activity code for the working-shifts, for the staffing. For each interval-time in each working-shift (ii) operating a forecast-adherence engine to yield the predicted adherence parameter; (iii) operating a coaching-aggregation engine to yield a coaching parameter; (iv) operating a time-off aggregation engine to yield a time-off parameter; (v) operating a shrinkage-calculator based on the predicted adherence parameter, the aggregated coaching parameter, and the aggregated time-off parameter, to yield a shrinkage parameter; (vi) configuring the WFM to automatically schedule staffing for the interval-time based on the yielded shrinkage parameter; (vii) storing the working-shift in a database and configuring the WFM application to automatically trigger a notification to each agent scheduled the working-shift.