Orna Raz

Automated Assistance for Eliciting User Expectations

2018 · KiltHub Repository

People often use software for mundane tasks and expect it to be dependable enough for their needs. Unfortunately, the incomplete and imprecise specifications of such everyday software inhibit many dependability enhancement techniques because these require …

Detection of data drift and outliers affecting machine learning model performance over time

2020 · arXiv (Cornell University)

A trained ML model is deployed on another `test' dataset where target feature values (labels) are unknown. Drift is distribution change between the training and deployment data, which is concerning if model performance changes. For …