Neural networks and rule extraction for prediction and explanation in the marketing domain

This paper contains a case study where neural networks are used for prediction and explanation in the marketing domain. Initially, neural networks are used for regression and classification to predict the impact of advertising from money invested in different media categories. Rule extraction is then performed on the trained networks, using the G-REX method, which is based on genetic programming. Results show that both the neural nets and the extracted rules outperform the standard tool See5. G-REX combines high performance with keeping the rules short to ensure that they really provide explanation and not obfuscation.