Essay

Why a weekly benchmark should not decide model rollbacks

Question: A team checks a held-out benchmark every Friday to monitor progress. Explain why using that same score to decide whether to keep the current model or revert to an earlier version is a bad practice, and describe what happens to the quality of the benchmark estimate.

Sample answer: If the benchmark is used to choose between models, it becomes part of the decision-making loop instead of serving only as a final check. Repeatedly using it in this way encourages the team to adapt the model to that benchmark, which makes the system overfit to the benchmark itself. Once that happens, the benchmark can no longer be trusted as a fully unbiased estimate of how well the model will perform in real use.

Key points:

  • Rollback decisions based on benchmark scores make the benchmark influence model selection.
  • That influence causes overfitting to the benchmark.
  • After overfitting, the benchmark is no longer a completely unbiased estimate of performance.

Rubric: The response should state that using benchmark results to choose whether to roll back a model causes overfitting to the benchmark. It should also explain that this overfitting weakens or removes the benchmark's ability to provide an unbiased performance estimate.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Machine Learning Strategy

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Yearning @ DeepLearning.AI