Track Descriptions | Schedule at a Glance | Speakers
Don will illustrate a modeling approach used by several well known retailers and travel agencies. Classification and Regression Trees are used to create a "Hot Spot Detector" methodology whereby a single terminal node of a Tree identifies an extremely homogenous subset of rare events (a needle in a haystack). This approach is utilized to segment a High Dimensional Database into a large number of small, highly concentrated/homogenous nodes contained in branches that span across the space of the database. These branches and nodes are then used as inputs into various predictive models or can be grouped to identify targetable subsegments.
Wednesday - 11:10 am - Capitol Room
Traditional querying and reporting analysis techniques can only take you so far in your quest to understand visitor behavior on your websites. Sometimes there is just too much data, too much noise, to be able to see the forest for the trees. After all that slicing and dicing it may be time to move on to using other tools in the analytical toolbox. In this presentation Neil will look at the use of a range of data mining and predictive analytical techniques to get to grips with issues like visitor segmentation and understanding customers' propensity to purchase. In this presentation Neil will look at how you can use data mining and predictive analytical techniques to get to grips with issues like visitor segmentation and understanding customers' propensity to purchase. Its where business meets math.
Wednesday - 1:30 pm - Capitol Room
Chris Gemignani, Juice Analytics
Reporting can help you when you know the questions to ask. But what about when you aren't sure if you are asking the right questions? This session will present techniques to help you find and explore patterns in data using Excel and other common tools. Some analyst fear that advanced data exploration is the purview of programmers we'll show you ways for non-technical analysts to make the most of free tools.
Wednesday - 2:30 pm - Capitol Room