Skip to main content
Home/Risks/Schnitzer2024/Inappropriate data splitting

Inappropriate data splitting

Category

"In data-driven AI development, the annotated data set is commonly split into training, validation, and test sets, whereby it is essential that the latter is not used for development but only for evaluation. Using the test set for training manipulates the testing strategy, which is the basis of the system’s quality assurance."(p. 10)

Other risks from Schnitzer2024 (24)