Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraints

TL;DR

DeCCaF is a novel learning-to-defer framework that models human error probabilities and optimizes deferral decisions under cost and workload constraints, improving decision accuracy in cost-sensitive scenarios.

Contribution

It introduces a new approach combining supervised learning and constraint programming to handle cost-sensitive deferral with limited human predictions and workload constraints.

Findings

Achieved an average 8.4% reduction in misclassification cost.

Performed well across various cost-sensitive fraud detection scenarios.

Outperformed baseline methods significantly.

Abstract

Learning to defer (L2D) aims to improve human-AI collaboration systems by learning how to defer decisions to humans when they are more likely to be correct than an ML classifier. Existing research in L2D overlooks key real-world aspects that impede its practical adoption, namely: i) neglecting cost-sensitive scenarios, where type I and type II errors have different costs; ii) requiring concurrent human predictions for every instance of the training dataset; and iii) not dealing with human work-capacity constraints. To address these issues, we propose the \textit{deferral under cost and capacity constraints framework} (DeCCaF). DeCCaF is a novel L2D approach, employing supervised learning to model the probability of human error under less restrictive data requirements (only one expert prediction per instance) and using constraint programming to globally minimize the error cost, subject to workload limitations. We test DeCCaF in a series of cost-sensitive fraud detection scenarios with different teams of 9 synthetic fraud analysts, with individual work-capacity constraints. The results demonstrate that our approach performs significantly better than the baselines in a wide array of scenarios, achieving an average $8.4\%$ reduction in the misclassification cost. The code used for the experiments is available at https://github.com/feedzai/deccaf