[IBM Data Analytics] Introduction to Data Analytics - Using Data Analysis for Detecting Credit Card Fraud (Peer-Graded Final Assignment_Answers/Reviews)

1. List at least 5 (five) data points that are required for the analysis and detection of a credit card fraud. (3 marks)

1.       Card holder / Customer Id

2.       Transaction date

3.       Transaction time

4.       Transaction value

5.       Shipping address

6.       IP address

7.       Device model

8.       Location

 

 

 

2. Refer to the data table below and identify 3 (three) errors/issues that could impact the accuracy of your findings. (3 marks)

• Missing transaction value
• Missing IP Address
• Date format inconsistency

 

 

3. Refer to the data table below and identify 2 (two) anomalies or unexpected behaviors, that would lead you to believe the transaction may be suspect. (2 marks)

• Significantly higher Transaction Value where Shipping Address has been changed from home/office address to P.O. Box.
• Higher Transaction Value and increased frequency of transactions.
• IP Address change and significantly higher Transaction Value.
• IP Address change and Shipping Address change

 

 

4. Briefly explain your key take-away from the provided data visualization chart. (1 mark)

• The visualization depicts the transaction values per transaction for all three users. The key take-away from this visualization is the sharp rise in the transaction values for users johnp and ellend, which may be indicative of an anomaly.

 

 

5. dentify the type of analysis that you are performing when you are analyzing historical credit card data to understand what a fraudulent transaction looks like. 

• Descriptive Analytics