TheMainstreamSeer

In today's post we will focus on "data understanding", which is a crucial aspect of all data mining projects.  Data understanding comes immediately after business understanding in the CRISP-DM methodology: Per IBM SPSS Modeler Help, the data understanding phase of CRISP-DM involves taking a closer look at the data available for mining.  It  involves accessing the data and exploring it using tables and graphics.  This enables you to determine the quality of the data and describe the results of these steps in the project documentation. To get started, I used a csv file that was sent to me recently.  I dragged a Var. File node onto the modeling canvas, attached the csv file to that node and then output the results into a table node.  On reviewing the results, it was clear to me that csv format was not working as desired - the data was not coming through in the correct columns as in the source file.  I then saved the source file as an Excel Workbook (2007, 2010) and repeat

SPSS Deployment is all about "operational-izing" the predictive models developed using SPSS Modeler.  Broadly, this includes Collaboration & Deployment Services (C&DS) and Decision Management (DM).  In today's blog, we will focus on C&DS. C&DS provides a secure foundation for analytics.  It provides the technology infrastructure to manage analytic assets (predictive models), share them securely throughout the enterprise and automate processes.  This enables an organization to make better decisions consistently. There are three aspects to C&DS: 1) Collaborate - C&DS makes it possible to share and re-use assets efficiently, protect them in ways that meet internal and external compliance requirements and publish results so that a greater number of business users can view and interact with results. 2)  Automate -  Automation enables the organization to make analytics a core component of the daily decision-making processes. You can construct flexi