Which option describes how data scarcity can be mitigated?

• A. Augmentation.
• B. Generating synthetic data.
• C. Imputing missing data.
• D. All of the above.

Answer: (D)

Mitigating data scarcity involves expanding and completing the dataset. Data augmentation increases the number of training examples by applying valid transformations to existing data, producing more samples without new data collection. Generating synthetic data uses models or simulations to create additional realistic data points that resemble the real distribution, helping when real data are limited. Imputing missing data fills in gaps by estimating plausible values for missing entries, enabling models to learn from a more complete dataset. Each method addresses a different aspect—quantity, realism, and completeness—so using all of them provides a comprehensive way to overcome limited data.