Final database marketing class

Good job Marketing 455 students! The students presented the final case, a Harvard one, entitled, "Pilgrim Bank" which is a study in how to determine the most profitable customers for a mythical bank. Students analyze the data in stages and at first it looks like online banking does not make a customer profitable but then we need to take age and income factors into account and when doing so, online banking is a factor in profitability. Students run various regression models and come up with the solution with the most explantory power. The students did well and were able to understand and analyze this advanced case. Their SPSS skills have improved and they were able to get to the heart of the case with some legwork. We also discussed what other types of data Pilgrim Bank might want to use to better understand its customers, both internal and external and how the Bank can manage customer relationshps for maximized lifetime value. Database Marketer extraordinary, Rob Jackson, an interactive marketing advisory board member, came to class and helped provide insight to our discussion. Thanks, Rob!

Database class update

I am so proud of my database marketing class. We have spent the last several weeks working on some non-statistical techniques of data analysis such as RFM, neural networking, decision trees and cluster techniques. We have also introduced the class to data mining as a discipline and the SPSS Clementine data mining software. The students were so familiar with SPSS that it took a while to get used to Clementine. Although Clementine has an 'easier to use' graphical interface, the students liked the control offered through the traditional SPSS interface. Clementine is more of a 'black box' environment, although it makes certain functions easier than in traditional SPSS. Some of the functions that are easier include neural networking, creating lifts and gains charts and comparting multiple models. Clementine also includes advanced graphics capabilities. I like being able to get a graphic representation of how large a cluster grouping is and the relative importance of different variables in creating the clusters. The students handed in their data mining assignment today. It was great seeing them play with the program and the data and get a real life taste of data mining.