For questions 6 – 9

Question

A large bank is interested in identifying the probability of fraudulent online purchases. The model below uses a variable, SimilarityScore, which considers similarity with past purchases, and an indicator variable for large transaction amounts. LargeTransaction (coded 1 if a transaction is greater than $1,000 and coded 0 if not) to explain the log-odds of fraudulent purchases (coded 1 if the transaction is fraudulent and coded 0 if not)

Ln(odds of purchase fraud) = 12 - 0.018*Similarity + 0.4*LargeTransaction

If a purchase has a SimilarityScore of 600 and a transaction amount of $1,200, what are the estimated odds that the purchase is fraudulent?

Answer 1

To calculate the estimated odds that the purchase is fraudulent, we can substitute the given values into the equation:

Ln(odds of purchase fraud) = 12 - 0.018*Similarity + 0.4*LargeTransaction

SimilarityScore = 600
LargeTransaction = 1 (transaction amount is greater than $1,000)

Ln(odds of purchase fraud) = 12 - 0.018*600 + 0.4*1
Ln(odds of purchase fraud) = 12 - 10.8 + 0.4
Ln(odds of purchase fraud) = 1.6

Now, we need to convert the natural logarithm (Ln) back to regular odds. We can calculate this by taking the exponent of both sides of the equation:

Odds of purchase fraud = e^(1.6)

Using a calculator, the estimated odds of the purchase being fraudulent is approximately 4.96.