The Risk of Optimization in Marketing Campaigns

In marketing one of the most common important tasks is to assign campaigns to sets of customers. These sets of customers, the target groups, consist of persons with similar properties, for example a high buying affinity for a certain product. Database marketers would not only assign a campaign by general economic or promotional consideration, but they take into account learning from databases by algorithms. The basic assumptions are already determined clusters to which campaigns, representing the products, should be assigned. The assignment can be done in the most optimal way by formal optimization, which is usually stochastic due to unknown campaign success in the future. The authors model the financial risk of the campaign success for enterprise practice. Their proposal is to use triangular distributions, known from financial and supply chain management applications. In an example, they demonstrate the benefits of the proposed procedure for the marketing task.