PDE Preparing and Using Data for Analysis Practice Question
You are using BigQuery ML to train a matrix factorization model for a recommendation system. The training data consists of user-item interactions. You notice that the model is overfitting. Which of the following hyperparameter changes would most likely reduce overfitting?
⚠ Common exam trap
PDE often tests the misconception that adding more capacity (more factors or more iterations) improves a model, when in fact those changes worsen overfitting and only stronger regularization reduces it.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Increase w_reg (regularization weight) from 0.1 to 0.5
Increasing w_reg raises the L2 regularization penalty applied to the learned latent factor matrices, which shrinks factor magnitudes and constrains model complexity. In BigQuery ML's matrix factorization, w_reg directly controls how strongly the optimizer penalizes large weights, so moving from 0.1 to 0.5 tightens the fit and reduces overfitting on sparse user-item interaction data.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Increase w_reg (regularization weight) from 0.1 to 0.5
Why this is correct
w_reg controls L2 regularization strength on the learned factors. Raising it from 0.1 to 0.5 penalises large factor values more heavily, constraining model complexity and reducing overfitting on the sparse user-item interaction data described in the stem.
- ✗
Decrease w_reg (regularization weight) from 0.1 to 0.01
Why it's wrong here
Decreasing regularization reduces penalty, likely increasing overfitting.
- ✗
Increase num_factors from 10 to 20
Why it's wrong here
Raising num_factors enlarges each user and item embedding, increasing model capacity so it memorises training interactions and overfits further. It tempts because num_factors controls latent dimensionality, and increasing it would be correct when the model underfits and cannot represent enough interaction structure.
- ✗
Increase num_training_iterations from 10 to 20
Why it's wrong here
More training iterations let the optimiser drive training loss lower, so the model continues fitting noise and overfitting intensifies. It tempts because num_training_iterations governs optimisation duration, and raising it would be right when the model has not yet converged and training loss is still falling.
Go deeper
Related to this question
About these practice questions
One of 747 original PDE practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
This PDE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PDE exam.