Fake Bills

The dataset includes 1500 rows and 7 columns:

• is_genuine: boolean
• diagonal: float
• height_left: float
• height_right: float
• margin_low: float
• margin_upper: float
• length: float

Idea of projects with this dataset:

• Predicting the missing values with a linear regression or a KNN imputer
• Comparing classification such as logistic regression or KNN with an unsupervised model such as K-Means to predict the authenticity of the bills
• Trying to do a PCA or a Kernel Transform to create a clearer separation between the Genuine and Fake Bills