This is a classic case of catastrophic forgetting.

When retraining only on recent data, the model adapts to new patterns while losing performance on older distributions. This is common in incremental learning setups.

To fix it, mix a representative sample of historical data into retraining or use rehearsal techniques. Regularization toward previous weights can also help.

Common mistakes:

1. Training only on the latest data window

2. Assuming more recent data is always better

3. Dropping legacy edge cases

Retraining should expand knowledge, not replace it.