Scenario: You're a data scientist working on a fraud detection system for an online payment platform. You have a limited dataset of $10$ transactions with four attributes:

Amount: $($Numerical: Transaction amount in dollars$)$

Device: $($Categorical: Type of device used for the transaction$)$

Location: $($Categorical: Country where the transaction originated$)$

Outcome: $($Binary: Fraudulent or Legitimate$)$

The data looks like this:

$\backslash$table$[[$Record$,$Amount,Device,Location,Outcome$],[1,100,$Mobile,USA,Fraudulent$],[2,50,$Desktop,UK$,$Legitimate$],[3,300,$Mobile,Spain,Fraudulent$],[4,20,$Tablet,Canada,Legitimate$],[5,75,$Desktop,USA,Legitimate$],[6,150,$Mobile,India,Fraudulent$],[7,40,$Tablet,Germany,Legitimate$],[8,80,$Deskitop,France,Legitimate$],[9,250,$Mobile,Brazil,Fraudulent$],[10,10,$Tablet,Australia,Legitimate$]]$

fraudulent.