| 来源类型 | Working Paper |
| 规范类型 | 报告 |
| DOI | 10.3386/w25854 |
| 来源ID | Working Paper 25854 |
| Simplicity Creates Inequity: Implications for Fairness, Stereotypes, and Interpretability | |
| Jon Kleinberg; Sendhil Mullainathan | |
| 发表日期 | 2019-05-20 |
| 出版年 | 2019 |
| 语种 | 英语 |
| 摘要 | Algorithms are increasingly used to aid, or in some cases supplant, human decision-making, particularly for decisions that hinge on predictions. As a result, two additional features in addition to prediction quality have generated interest: (i) to facilitate human interaction and understanding with these algorithms, we desire prediction functions that are in some fashion simple or interpretable; and (ii) because they influence consequential decisions, we also want them to produce equitable allocations. We develop a formal model to explore the relationship between the demands of simplicity and equity. Although the two concepts appear to be motivated by qualitatively distinct goals, we show a fundamental inconsistency between them. Specifically, we formalize a general framework for producing simple prediction functions, and in this framework we establish two basic results. First, every simple prediction function is strictly improvable: there exists a more complex prediction function that is both strictly more efficient and also strictly more equitable. Put another way, using a simple prediction function both reduces utility for disadvantaged groups and reduces overall welfare relative to other options. Second, we show that simple prediction functions necessarily create incentives to use information about individuals' membership in a disadvantaged group—incentives that weren't present before simplification, and that work against these individuals. Thus, simplicity transforms disadvantage into bias against the disadvantaged group. Our results are not only about algorithms but about any process that produces simple models, and as such they connect to the psychology of stereotypes and to an earlier economics literature on statistical discrimination. |
| 主题 | Econometrics ; Estimation Methods ; Microeconomics ; Economics of Information ; Health, Education, and Welfare ; Poverty and Wellbeing ; Labor Economics ; Labor Discrimination ; Other ; Law and Economics |
| URL | https://www.nber.org/papers/w25854 |
| 来源智库 | National Bureau of Economic Research (United States) |
| 引用统计 | |
| 资源类型 | 智库出版物 |
| 条目标识符 | http://119.78.100.153/handle/2XGU8XDN/583527 |
| 推荐引用方式 GB/T 7714 | Jon Kleinberg,Sendhil Mullainathan. Simplicity Creates Inequity: Implications for Fairness, Stereotypes, and Interpretability. 2019. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 资源类型 | 版本类型 | 开放类型 | 使用许可 | ||
| w25854.pdf（530KB） | 智库出版物 | 限制开放 | CC BY-NC-SA | 浏览 | ||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
