Rethinking and Recomputing the Value of Machine Learning Models
This addresses the gap between ML evaluation and practical application for organizations using AI in decision-making, though it is incremental as it builds on existing calibration and cost-sensitive learning concepts.
The paper tackles the problem that traditional ML metrics like accuracy fail to capture real-world value in hybrid human-AI workflows, proposing a new 'value' metric that incorporates task-specific costs and showing it leads to better model choices, with experiments indicating simple, well-calibrated models can outperform complex ones.
In this paper, we argue that the prevailing approach to training and evaluating machine learning models often fails to consider their real-world application within organizational or societal contexts, where they are intended to create beneficial value for people. We propose a shift in perspective, redefining model assessment and selection to emphasize integration into workflows that combine machine predictions with human expertise, particularly in scenarios requiring human intervention for low-confidence predictions. Traditional metrics like accuracy and f-score fail to capture the beneficial value of models in such hybrid settings. To address this, we introduce a simple yet theoretically sound "value" metric that incorporates task-specific costs for correct predictions, errors, and rejections, offering a practical framework for real-world evaluation. Through extensive experiments, we show that existing metrics fail to capture real-world needs, often leading to suboptimal choices in terms of value when used to rank classifiers. Furthermore, we emphasize the critical role of calibration in determining model value, showing that simple, well-calibrated models can often outperform more complex models that are challenging to calibrate.