Google Cloud Professional Data Engineer — Question 113

You work on a regression problem in a natural language processing domain, and you have 100M labeled examples in your dataset. You have randomly shuffled your data and split your dataset into train and test samples (in a 90/10 ratio). After you trained the neural network and evaluated your model on a test set, you discover that the root-mean-squared error (RMSE) of your model is twice as high on the train set as on the test set. How should you improve the performance of your model?

Answer options

• A. Increase the share of the test sample in the train-test split.
• B. Try to collect more data and increase the size of your dataset.
• C. Try out regularization techniques (e.g., dropout of batch normalization) to avoid overfitting.
• D. Increase the complexity of your model by, e.g., introducing an additional layer or increase sizing the size of vocabularies or n-grams used.

Correct answer: D

Explanation

The correct answer is D because increasing the complexity of the model can help it learn more intricate patterns in the data, which is necessary when the training performance is poor. Option A is not effective as it doesn't address the model's learning capability, B may help but is not an immediate solution, and C is focused on reducing overfitting rather than addressing the underperformance on the training set.