Try it on paper first. A hint, the key idea and the worked solution are here when you need them.
A bank wants software to decide which card payments might be fraud. Two designs are suggested.
Compare the two designs. Give one advantage of each, and say which you would choose if criminals keep changing their methods. (4 marks)
Machine learning is when a program has the ability to automatically adapt its own processes and/or data. It learns from examples (training data). An expert system's rules are written by people; a learning program adapts its own rules and data.
Have you tried it?
Work it out on paper first. It is fine to get stuck or make a mistake: that is how we learn. When you are ready, go through the solution one step at a time, and check each step against your own.
Design A, an advantage. Its rules come from experts and can be read, so the bank can explain why a payment was stopped. It works from the start, without needing millions of labelled payments.
Design B, an advantage. It finds patterns in a huge amount of data that experts might never notice, and it adapts its own data and processes as new labelled payments arrive.
The choice. Design B, because criminals change their methods. A learning program adapts automatically to new patterns in the data. An expert system keeps its old rules until people write new ones, so it falls behind.
Watch out. "Compare" needs a point about both designs, not two separate descriptions. A good answer could also say that B's reasons are harder to explain, so the bank might use both.
Log in to join the discussion.
Loading…