Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraints
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
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: All changes suggested by the reviewer were implemented, except for newer experiments on different datasets, as justified in the previous message.
Notational changes were also made to facilitate the interpretation of Algorithm 1 and of section 3, nominally changing the point-wise loss expression in section 3.4 to $\ell$ to differentiate it from the empirical loss. Clearer references to specific equations were also introduced.
Video: https://www.youtube.com/watch?v=R51SBj02RuU
Code: https://github.com/feedzai/deccaf
Assigned Action Editor: ~Aditya_Menon1
Submission Number: 2368
Loading