Paolo Amoroso posed an interesting
question on the comp.ai newsgroup
(yes newsgroups still exist!) regarding what has happened to Expert Systems
since the AI Winter.
He got some very enlightening responses on what
has happened with these systems since their introduction a couple of decades
ago. Here is a choice quote from one of the replies:
In financial fraud detection, particularly the problem of finding
credit card transaction fraud, expert systems were an early candidate.
Based on experts’ experience, rules were posed which characterized
known fraud and the output on unseen data was used to figure out how
the rules would go wrong. These systems did as well as the state of
the art at the time which was considerably worse than the state of the
art now.
Go right to the discussion
Paolo’s blog post on Expert Systems
Paolo’s blog post on LISA and rule-based Programming
