AWS wellarchitected documentation change
Summary
Formatting changes (quotes to italics), figure numbering update, reordered bullet points about feature engineering components, and minor wording adjustments in technical explanations
Security assessment
Changes focus on formatting, figure references, and reordering/rewording of technical concepts related to machine learning feature engineering. No mention of vulnerabilities, security controls, or protective measures. Dimensionality reduction techniques (PCA/ICA/LDA) are standard ML practices for efficiency, not security-specific.
Diff
diff --git a/wellarchitected/latest/machine-learning-lens/feature-engineering.md b/wellarchitected/latest/machine-learning-lens/feature-engineering.md index 1b08eced1..c630ea0ce 100644 --- a//wellarchitected/latest/machine-learning-lens/feature-engineering.md +++ b//wellarchitected/latest/machine-learning-lens/feature-engineering.md @@ -7 +7 @@ -Every unique attribute of the data is considered a “feature” (also known as “attribute”). For example, when designing a solution for predicting customer churn, the data used typically includes features such as customer location, age, income level, and recent purchases. +Every unique attribute of the data is considered a _feature_ (also known as an _attribute_). For example, when designing a solution for predicting customer churn, the data used typically includes features such as customer location, age, income level, and recent purchases. @@ -9 +9 @@ Every unique attribute of the data is considered a “feature” (also known as - + @@ -11 +11 @@ Every unique attribute of the data is considered a “feature” (also known as -_Figure 11: Feature engineering main components_ +_Figure 10: Feature engineering main components_ @@ -13 +13 @@ _Figure 11: Feature engineering main components_ -Feature engineering is a process to select and transform variables when creating a predictive model using machine learning or statistical modeling. Feature engineering typically includes feature creation, feature transformation, feature extraction, and feature selection as listed in Figure 11. With deep learning, feature extraction is automated as part of the algorithm learning. +Feature engineering is a process to select and transform variables when creating a predictive model using machine learning or statistical modeling. Feature engineering typically includes feature creation, feature transformation, feature extraction, and feature selection as listed in Figure 10. With deep learning, feature engineering is automated as part of the algorithm learning. @@ -15 +15 @@ Feature engineering is a process to select and transform variables when creating - * **Feature selection** is the process of selecting a subset of extracted features. This is the subset that is relevant and contributes to minimizing the error rate of a trained model. Feature importance score and correlation matrix can be factors in selecting the most relevant features for model training. + * _Feature creation_ refers to the creation of new features from existing data to assist with better predictions. Examples of feature creation include one-hot-encoding, binning, splitting, and calculated features. @@ -17 +17 @@ Feature engineering is a process to select and transform variables when creating - * **Feature transformation and imputation** include steps for replacing missing features or features that are not valid. Some techniques include: forming Cartesian products of features, non-linear transformations (such as binning numeric variables into categories), and creating domain-specific features. + * _Feature transformation and imputation_ include steps for replacing missing features or features that are not valid. Some techniques include forming Cartesian products of features, non-linear transformations (such as binning numeric variables into categories), and creating domain-specific features. @@ -19 +19 @@ Feature engineering is a process to select and transform variables when creating - * **Feature creation** refers to the creation of new features from existing data to help with better predictions. Examples of feature creation include: one-hot-encoding, binning, splitting, and calculated features. + * _Feature extraction_ involves reducing the amount of data to be processed using dimensionality reduction techniques. These techniques include Principal Components Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA). This reduces the amount of memory and computing power required, while still accurately maintaining original data characteristics. @@ -21 +21 @@ Feature engineering is a process to select and transform variables when creating - * **Feature extraction** involves reducing the amount of data to be processed using dimensionality reduction techniques. These techniques include: Principal Components Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA). This reduces the amount of memory and computing power required, while still accurately maintaining original data characteristics. + * _Feature selection_ is the process of selecting a subset of extracted features. This is the subset that is relevant and contributes to minimizing the error rate of a trained model. Feature importance score and correlation matrix can be factors in selecting the most relevant features for model training. @@ -34 +34 @@ Data preprocessing -Operational excellence pillar best practices +Model development