Skip to content
- Dimensionality reduction can improve visualization and efficiency.
a) True
- PCA is used to reduce dimensionality.
a) True
- Preprocessing decisions can affect model outcomes
a) True
- Data leakage improves the fairness of evaluation.
a) False
- Normalization and standardization are forms of feature scaling.
a) True
- Clustering is a common unsupervised learning task.
a) True
- Unsupervised learning cannot reveal patterns in data.
a) False
- Unsupervised learning works with unlabeled data.
a) True
- Data cleaning is irrelevant if the dataset is large.True
a) False
- Data preprocessing can include cleaning, scaling, and transforming features.
a) True
- K-means requires labeled outcomes to form clusters.
a) False
- Unsupervised learning is often used in exploratory analysis.
a) True
- Clustering can support customer segmentation.
a) True
- Visualization can help interpret cluster structure.
a) True
- Scaling numeric features can change distance relationships.
a) True
- Outliers can distort clustering results.
a) True
- Feature scaling is important for distance-based algorithms.
a) True
- Missing values should always be left unchanged.
a) False
- Noise in data can reduce analytical reliability.
a) True
- Tokenization is primarily a text preprocessing technique.
a) True
Post Views: 39
