Decision-Aware Predictive Model Selection for Workforce Allocation

TL;DR

A novel framework that utilizes machine learning to predict worker behavior and employs integer optimization to strategically assign workers to tasks and offers context-sensitive and data-responsive strategies for workforce management is introduced.

Abstract

Many organizations depend on human decision-makers to make subjective decisions, especially in settings where information is scarce. Although workers are often viewed as interchangeable, the specific individual assigned to a task can significantly impact outcomes due to their unique decision-making processes and risk tolerance. In this paper, we introduce a novel framework that utilizes machine learning to predict worker behavior and employs integer optimization to strategically assign workers to tasks. Unlike traditional methods that treat machine learning predictions as static inputs for optimization, in our approach, the optimal predictive model used to represent a worker's behavior is determined by how that worker is allocated within the optimization process. We present a decision-aware optimization framework that integrates predictive model selection with worker allocation. Collaborating with an auto-insurance provider and using real-world data, we evaluate the effectiveness of our proposed method by applying three different techniques to predict worker behavior. Our findings show the proposed decision-aware framework outperforms traditional methods and offers context-sensitive and data-responsive strategies for workforce management.

Figures (9)

• Figure 1: Comparison of the test set AUC between individual and aggregate predictive models for each underwriter, with the grey dashed line indicating where the individual and aggregate models achieve equal AUC values.
• Figure 2: Out-of-sample Positive Predictive Value (PPV) and False Omission Rate (FOR) of the aggregate predictive model when applied to fifteen underwriters.
• Figure 3: In-sample true positive and true negative rates are used to cluster workers for the creation of profile predictive models.
• Figure 4: ROC curves and AUC values illustrating the predictive power of the proposed predictive models.
• Figure 5: Expected profit increase compared to random worker allocation when different behavioral predictive models are used in the optimization framework.