Mastering Predictive Analytics with Python

Case study: targeted e-mail campaigns

In our next example, our same marketing department wants to promote new items on their website to users who are mostly likely to be interested in purchasing them. Using a predictive model that includes features from both users and these new items, customers are sent e-mails containing a list of their most probable purchase. Unlike the real-time sentiment-monitoring example, e-mails are sent in batches and use data accumulated over a customer's whole transaction history as inputs to the model, which is a better fit for batch processing.

An overview of the processes used in this example is shown in Figure 7.

Figure ...