neural networks

the use of neural networks for credit assessment is still relatively in its infancy and the purpose of this short section is mainly to record that they exist and have great potential to bring effective use of technology to judgmental credit decisions.
A neural network is a computer program that can learn from its experience.unlike credit scoring and expert system ,which have their rules set for them , neural networks are self-training that can take experiences and derive new rules from them. They do not function in the same way as human brains but they are more like brains than most computer. they can learn from experience by following set procedural principle. some models can do pattern matching and they can also take on board contextual differences . for example ,they can tell the difference between a painting of a human and one of apple in a still life . Instead of proceeding by hard and fast logical rules , they deal with information by a process that is roughly similar to what we call associative or analogical thinking .
The potential power of a computer that can learn is obvious ;watch this space .