Alternative Shift Generation for Flexible Contact Center Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contact centers face challenges in optimizing agent scheduling due to high turnover, labor laws, agent specialization, and the desire to provide scheduling autonomy while maintaining service levels, which complicates traditional scheduling methods.
Innovation Solution
A system utilizing AI forecasting and column generation with linear programming and constraint programming to create a scalable, multi-objective agent scheduling system, allowing agents to trade shifts through alternative shifts that meet organizational performance goals and individual preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If agents are provided with scheduling autonomy to control portions of their schedules, then agent motivation is increased and turnover is decreased, but the difficulty of determining the most optimal scheduling solution that minimizes costs and meets constraints is increased
Solution Approach 1:
The scheduling problem is segmented into multiple components: a master scheduling system that handles global optimization, and individual agent schedule modification capabilities. The system divides the complex optimization into a master problem (overall staffing requirements) and sub-problems (individual agent preferences and constraints), allowing agents to control portions of their schedules while maintaining overall optimization.
Solution Approach 2:
The scheduling system is made dynamic by allowing agents to request and trade shifts within certain constraints. The system continuously adjusts schedules based on real-time requests while maintaining optimization goals. This dynamic approach enables agents to have control over their schedules without compromising the overall optimal solution, as the system adapts to individual requests while preserving global efficiency.
2Productivity
If traditional scheduling methods are used to minimize costs and meet constraints, then optimal scheduling solutions can be determined, but the ability to provide agents with schedule control and reduce turnover is limited
Solution Approach 1:
The scheduling system is designed to serve multiple functions simultaneously: it optimizes costs, meets business constraints, accommodates agent preferences, and enables shift trading. This multi-functional approach allows the same system to handle both organizational goals and individual agent needs, providing versatility that traditional single-function scheduling methods cannot achieve.
Solution Approach 2:
The system incorporates feedback mechanisms where agents can request schedule changes, and the system evaluates these requests against optimization goals and constraints. This feedback loop allows the system to adapt to agent preferences while maintaining overall scheduling efficiency, creating a responsive system that balances organizational needs with individual desires.
3Reliability
If a large number of agents are hired to directly interface with customers, then service levels can be maintained, but the costs associated with providing service are increased
Solution Approach 1:
The system performs preliminary scheduling optimization to determine the minimum number of agents needed to meet service levels. By proactively optimizing schedules before peak demand periods, the system can maintain service levels with fewer agents. The system predicts workload patterns and pre-allocates agents accordingly, avoiding the need to hire excess staff during low-demand periods.
Solution Approach 2:
The system changes scheduling parameters such as shift lengths, break times, and scheduling frequencies to optimize the agent-to-customer ratio. By adjusting these parameters dynamically based on predicted workload, the system can maintain adequate service levels with a reduced number of agents, as the same agents can be scheduled more efficiently to match actual demand patterns.
Data Source
AI summary
A system for generating alternative shifts for contact center agent scheduling according to an embodiment includes a system that receives a staffing requirement forecast indicative of a number of agents required to handle a workload forecast. Agent data is received for a plurality of agents. The system receives a service level override value and performs column generation to identify shifts for the agents based on the staffing requirement forecast, agent working rules, and work plan constraints. A subset of the shifts is selected to generate an optimized agent shift schedule. A request to replace an individual shift of the optimized shift schedule with an alternative shift is received. In response, the system identifies the alternative shift from the plurality of shifts based on the service level override value. The individual shift is replaced with the identified alternative shift on the optimized shift schedule.