Item Infomation
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Giovanni De, Toni | - |
dc.contributor.author | Bruno, Lepri | - |
dc.contributor.author | Andrea, Passerini | - |
dc.date.accessioned | 2023-03-30T09:07:07Z | - |
dc.date.available | 2023-03-30T09:07:07Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | https://link.springer.com/article/10.1007/s10994-022-06293-7 | - |
dc.identifier.uri | https://dlib.phenikaa-uni.edu.vn/handle/PNK/7347 | - |
dc.description | CC BY | vi |
dc.description.abstract | Being able to provide counterfactual interventions—sequences of actions we would have had to take for a desirable outcome to happen—is essential to explain how to change an unfavourable decision by a black-box machine learning model (e.g., being denied a loan request). Existing solutions have mainly focused on generating feasible interventions without providing explanations of their rationale. Moreover, they need to solve a separate optimization problem for each user. | vi |
dc.language.iso | vi | vi |
dc.publisher | Springer | vi |
dc.subject | interventions—sequences of actions | vi |
dc.subject | black-box machine learning model | vi |
dc.title | Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis | vi |
dc.type | Book | vi |
Appears in Collections | ||
OER - Công nghệ thông tin |
Files in This Item: