Comparing frequency & recency
Now that you've created frequency and recency features, let's compare them between the legitimate transactions and the fraudulent ones. The dataset transfers
contains 222 transactions from 4 accounts. The frequency features freq_channel
and freq_auth
, and the recency features rec_channel
and rec_auth
have been added as columns to the dataset.
This exercise is part of the course
Fraud Detection in R
Exercise instructions
- Have a look at dataset
transfers
in the console using functions likehead
andstr
. - Get a summary of the frequency and recency channels for legitimate transactions.
- Get a summary of the frequency and recency channels for fraudulent transactions.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
library(dplyr)
# Statistics of frequency & recency features of legitimate transactions:
summary(transfers %>% filter(___) %>% select(___, ___, ___, ___))
# Statistics of frequency & recency features of fraudulent transactions:
summary(transfers %>% filter(___) %>% select(___, ___, ___, ___))