用数学方法公平分配金融模型中各特征的风险贡献。
Explaining Risks: Axiomatic Risk Attributions for Financial Models
- 基于谢帕利值框架扩展风险分配方法
- 实证表明可精准分解模型风险来源
- 适合金融风控、模型可解释性研究者
近年来，机器学习模型虽取得显著成果，但其复杂的黑箱结构带来解释难题。通过使用公理化归因方法，可公平分配各特征对预测的贡献，从而实现模型可解释性。在金融等高风险领域，风险本身与平均预测同样重要。本文解决的核心问题是：如何根据模型和数据公平分配风险？通过分析与实证案例，我们证明可通过扩展谢帕利值框架有效实现风险分配。
原文摘要 · Abstract (English)
In recent years, machine learning models have achieved great success at the expense of highly complex black-box structures. By using axiomatic attribution methods, we can fairly allocate the contributions of each feature, thus allowing us to interpret the model predictions. In high-risk sectors such as finance, risk is just as important as mean predictions. Throughout this work, we address the following risk attribution problem: how to fairly allocate the risk given a model with data? We demonstrate with analysis and empirical examples that risk can be well allocated by extending the Shapley value framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。