Module 2 challenge :The Nuts and Bolts of Machine Learning (Google Advanced Data Analytics Professional Certificate) Answers 2025

1. Feature engineering

❌ Feature engineering does not involve using a data professional’s statistical knowledge.
✔ Feature engineering may involve transforming the properties of raw data.
✔ Feature selection involves choosing features that contribute the most to predicting the response.
✔ Feature extraction involves creating new features from multiple existing ones to improve accuracy.

---

2. Class imbalance resolution

✔ Downsampling
❌ Merging
❌ Upsampling
❌ Smoothing

---

3. Customer churn

✔ using a product or service
❌ reviewing items online
❌ sharing feedback with a company
❌ researching a company’s offerings

---

4. Bayes’s theorem

❌ Data accuracy
❌ Margin of error
❌ Causation
✔ Posterior probability

---

5. MinMaxScaler normalization

❌ 0.5
❌ -1
❌ 0.1
✔ 0

---

6. PACE stage

❌ Plan
❌ Analyze
❌ Construct
✔ Execute

---

7. Predictive feature

❌ Irrelevant
❌ Interactive
✔ Predictive
❌ Redundant

---

8. Log normalization

❌ binomial
✔ skewed
❌ probability
❌ normal

---

9. Spam filter evaluation

❌ Data too small
❌ Data perfectly balanced
✔ Data is imbalanced, precision and recall are useful
❌ Possible errors in data

---

10. Probability of A given B

✔ Bayes Theorem
❌ No Free Lunch Theorem
❌ Law of Large Numbers
❌ Central Limit Theorem

---

✅ Summary Table

---