A skating-pond thickness model was fit on mid-winter sensor rows. Late-season rows are warmer and noisier. What should the tester name that change?
Select an answer to reveal the explanation.
Short Explanation
A thickness model fit on mid-winter sensor rows now seeing warmer, noisier late-season rows is data drift: the statistical properties of operational input data have changed versus training. That is not concept drift (the meaning of the same row), not a Chapter 5 type clash, and not a reason to skip the watch.
Full Explanation
Data drift is a change in operational input-data statistics versus training. Calling it only concept drift, overfitting, or a Chapter 5 completeness gap names the wrong phenomenon.