In all industries, including on-line marketing, when talking about forecasting customer behavior and predictive analytics, the first thoughts that come to mind are complexity and cost. The traditional way of deploying and executing predictive analytics usually involves the purchase of expensive software and hardware as well as a lengthy process of rewriting data transformations and the model itself in an environment other than the one used to develop the model.
This picture has changed considerably with the advent of PMML (Predictive Model Markup Language), the de facto standard to represent predictive models. PMML allows models to be represented in a single and concise format across disparate environments. The advent of cloud computing and SaaS (Software as a Service) add to the new way of deploying and executing predictive models, since now there is no need to spend an arm and a leg on software and hardware licenses.
Given that PMML is now supported by most of the packages used to build predictive models (e.g. R, SAS, SPSS, KXEN, KNIME, …), it can be easily moved around. So much so that it can also be moved to the Cloud. Zementis is currently offering its PMML-based decision engine, called ADAPA, in the Amazon Cloud as a Service for as low as $.99 hour. PMML models can be easily uploaded into ADAPA and made available for execution in a matter of minutes. To make it even simpler, just recently, Zementis released the ADAPA add-in for Excel 2007 (available for free). This is truly a revolution since now anyone in the enterprise is able to score data in Excel by executing models previously deployed in the Cloud.
ADAPA allows for real-time scoring of customers at any time a new event occurs since it can be used from inside any application via Web Service Calls. Excel is just one such application which happens to be a very well known tool (used by many). This is remarkable, since it frees users from having to deal with all the technology required for scoring customers whenever necessary (and have the time to truly enjoy their morning coffee). With the Excel add-in, all one has to do is to select which group of customers to score (or the columns and rows containing the relevant data) and pressing on the “Score” button in Excel … et voila’ … new predictions are generated automatically for all selected records. It does not get easier than this.
If you want to just sit back and relax and watch the Excel add-in at work, feel free to take a look at the on-line video tutorial.