Problem: A data mining routine has been applied to a transaction dataset and has classified 88 records as fraudulent (30 correctly so) and 952 as nonfraudulent (920 correctly so).
a) Lowering the cutoff below 0.5, leads to classifying more nonfraudulent records as fraudulent records (more 0's are misclassified as 1's)
b) Lowering the cutoff below 0.5 leads to classifying more fraudulent records as nonfraudulent records (more 1's are misclassified as 0's)