In the context of preparing a dataset for machine learning, a data scientist is tasked with evaluating the quality of the data before model training. The dataset contains a mix of numerical and categorical variables, with some missing values and potential outliers. The data scientist must ensure the data is clean, consistent, and suitable for the intended machine learning models. Considering the need for a thorough understanding of the dataset's characteristics and quality, which of the following is the primary purpose of conducting exploratory data analysis (EDA) in this scenario? Choose one correct option.