1.2 Data Preprocessing

[MR-NBD]

Data exploration and preprocessing

As a preprocessing step, convert categorical features to numerical features, e.g., by means of a one-hot encoding, and apply a normalization to map all features between [0, 1]. Assign labels to the dataset indicating the true loan attribution outcomes for supervised learning. Clearly define categories or classes representing loan approval or denial. Additionally, reserve 20% of the dataset for final testing and assessment of the robustness of the models.

[Distii]

Completato ma con forse qualche dettaglio in più che va aggiunto nel report