Anonymized Industry Benchmark Forecasting for Workforce Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Workforce management predictive models in contact centers are limited by the lack of historical data for new business units and are affected by changes in products, services, or business volume, making it difficult to ensure accurate forecasting and alignment with industry behaviors.
Innovation Solution
The integration of anonymized industry data and classification codes into workforce management predictive models, allowing new customer business units to share and aggregate data across a wide range of industries, which is then used to drive forecasting and staffing decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If workforce management predictive models use only a customer business unit's historic data, then the models can be simple to implement, but new business units without historic data cannot be forecasted accurately
Solution Approach 1:
The patent combines a customer's own historical contact data with anonymized industry benchmark data from multiple sources into a unified predictive model input. This merging allows new business units to leverage industry-wide patterns while established units benefit from both their proprietary data and external benchmarks, resolving the contradiction between adaptability to new units and reliability of predictions.
Solution Approach 2:
Anonymized industry benchmark data serves as an intermediary that bridges the gap for new business units lacking historical data. The anonymization process protects customer privacy while allowing the benchmark data to provide reliable forecasting patterns that can be applied to new customers, enabling forecastability without compromising individual data privacy or model reliability.
2Loss of information
If workforce management predictive models rely on a single customer's historic data, then data privacy is maintained, but industry-specific benchmarks and comparisons cannot be provided
Solution Approach 1:
Anonymized industry benchmark data acts as an intermediary that enables industry-wide comparisons and benchmarks without exposing individual customer data. The anonymization process removes identifying information while preserving the statistical patterns and trends necessary for benchmarking, thus protecting data privacy while enabling industry-specific insights and comparisons.
Solution Approach 2:
The system creates a universal anonymized industry benchmark dataset that serves multiple customers simultaneously. This single anonymized dataset can be used to provide benchmarks across different industries and business units, enabling universal applicability while maintaining individual data privacy through the anonymization process.
3Measurement precision
If workforce management systems use extensive historical data for predictive modeling, then forecast accuracy improves, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent merges a customer's limited historical data with extensive anonymized industry benchmark data to achieve high forecast accuracy without requiring the customer to collect and process large volumes of their own historical data. This combination provides the statistical power of extensive data while keeping the customer's system complexity low.
Solution Approach 2:
Industry benchmark data is pre-processed, anonymized, and aggregated in advance into ready-to-use datasets. This preliminary action eliminates the need for customers to perform complex data collection, cleaning, and processing operations, reducing system complexity while still providing the accuracy benefits of extensive historical analysis.
Data Source
AI summary
A method for providing anonymized contact information to a workforce management system includes receiving contact information from a plurality of customer business units; assigning each of the plurality of customer business units one or more industry classification codes or product classification codes; anonymizing, by a processor, the contact information to the one or more industry classification codes or product classification codes; receiving, by a processor, a query from a workforce management system for anonymized contact information in one or more industry classification codes or product classification codes; and providing the anonymized contact information to the workforce management system for use in a workforce management predictive model.