Which approach is primarily used to handle categorical features? A: *One hot encoding B: Mean imputation C: Outlier removal D: Data normalization

How do we deal with missing data? A: Outlier removal B: *Mean imputation C: Normalization D: Data conversion

What is one way to detect outliers? A: *Identifying data points that fall outside of a certain range B: Data conversion C: Feature selection D: Data standardization

What is the most common way to normalize data? A: *Scaling the input data in order to transform it into a range of 0 to 1 B: Feature selection C: Data conversion D: One hot encoding

How do we differentiate between categorical and numerical features? A: *Categorical features are discrete values while numerical features are continuous values B: Feature selection C: Outlier removal D: One hot encoding

What are the main advantages of standardization? A: *Increases the correlation among features and can help improve model performance B: Data conversion C: One hot encoding D: Data normalization

What is the purpose of one hot encoding? A: *To transform categorical values into binary representation B: Feature selection C: Data normalization D: Outlier Removal

What type of data we should use outlier detection on? A: *Numerical data B: Categorical data C: Data normalization D: Data standardization

What is an example of a numerical feature? A: *Age B: Gender C: Data normalization D: Data conversion

When should we first use data normalization? A: *Before training the model B: After training the model C: Feature selection D: Outlier removal