Targeting direct marketing campaigns by neural networks

Abstract

Abstract Market-oriented companies increasingly aim at maximising the return of targeted direct marketing campaigns, rather than trying to reach customers and prospects indistinctly, according to a mass marketing approach. The profitability of direct marketing campaigns depends on a detailed definition of prospects and an accurate prediction of the response rate. This study shows how the use of Artificial Neural Networks (ANNs) can improve the effectiveness of direct mail marketing campaigns thanks to a better prediction of the response rate for subjects included in the target population according to factors that are believed to have an impact on their purchase intention. Results show the effectiveness of ANNs – in comparison with multiple regression analysis and logistic regression analysis – in identifying complex relationships among the data, and particularly in profiling customers and prospects and anticipating their behaviour.