Introduction to k Nearest Neighbour Classification and Condensed Nearest Neighbour Data Reduction

Suppose a bank has a database of people’s details and their credit rating. These details would probably be the person’s financial characteristics such as how much they earn, whether they own or rent a house, and so on, and would be used to calculate the person’s credit rating. However, the process for calculating the credit rating from the person’s details is quite expensive, so the bank would like to find some way to reduce this cost. They realise that by the very nature of a credit rating, people who have similar financial details would be given similar credit ratings. Therefore, they would like to be able to use this existing database to predict a new customer’s credit rating, without having to perform all the calculations.