Sibyl: Explaining Machine Learning Models for High-Stakes Decision Making
Autor: | Alexandra Zytek, Rhema Vaithianathan, Dongyu Liu, Kalyan Veeramachaneni |
---|---|
Rok vydání: | 2021 |
Předmět: |
business.industry
Computer science media_common.quotation_subject 05 social sciences Dashboard (business) 020207 software engineering Context (language use) 02 engineering and technology Machine learning computer.software_genre Domain (software engineering) User studies Sibyl 0202 electrical engineering electronic engineering information engineering Feature (machine learning) 0501 psychology and cognitive sciences Artificial intelligence business computer Welfare 050107 human factors media_common Interpretability |
Zdroj: | CHI Extended Abstracts |
Popis: | As machine learning is applied to an increasingly large number of domains, the need for an effective way to explain its predictions grows apace. In the domain of child welfare screening, machine learning offers a promising method of consolidating the large amount of data that screeners must look at, potentially improving the outcomes for children reported to child welfare departments. Interviews and case-studies suggest that adding an explanation alongside the model prediction may result in better outcomes, but it is not obvious what kind of explanation would be most useful in this context. Through a series of interviews and user studies, we developed Sibyl, a machine learning explanation dashboard specifically designed to aid child welfare screeners’ decision making. When testing Sibyl, we evaluated four different explanation types, and based on this evaluation, decided a local feature contribution approach was most useful to screeners. |
Databáze: | OpenAIRE |
Externí odkaz: |