A Machine Learning Specialist is preparing a dataset to train a predictive model. The model aims to project whether an applicant is eligible or not for a personal loan. The dataset contains numerical, categorical, and ordinal features. To increase prediction accuracy, the Specialist first analyzes the dataset using summary statistics to understand the features' distribution, central tendency, and variability. After gaining insights from the data analysis, the Specialist determines that it is necessary to transform categorical features into numerical values. Which method of feature engineering is the MOST suitable for this task?