Business Knowledge Series course

This course is intended for analysts working with virtually any type of exploratory data analysis problem. Discovery in a complicated data set is one of the analyst's toughest problems. The course covers this discovery process using many real-world problems. There is a focus on fraud detection, with the recognition that the core principles of modeling to solve fraud detection are the basis of all exploratory data analysis. Analytical methods used in the course include decision trees, logistic regression, neural networks, link analysis, and social network analysis. In addition, analysts receive practical advice on presenting complex findings to their audience.

Learn how to

• analyze in multiple dimensions
• escape the limits of common methods
• explore your most complex problems
• successfully present findings to your audience
• find rare events
• find hidden relationships
• reach deep into your data and find what others cannot.

Who should attend

Data analysts (market researchers, fraud researchers, and sales analysts); expert modelers or those who want to become expert; and the creative and curious

Formats available	Standard duration
Classroom:	2.0 days

To maximize the return on investment from the class, you should have the following skills and experience:

• background in analytical methods
• experience with predictive modeling
• familiarity with Base SAS, SAS/STAT, and SAS/GRAPH software, which you can acquire by taking the SAS Programming 1: Essentials or Statistics 1: Introduction to ANOVA, Regression, and Logistic Regression course.

This class is taught in SAS Enterprise Miner and foundation SAS. Familiarity with SAS Enterprise Miner at the level presented in the Applied Analytics Using SAS Enterprise Miner course is helpful. Most of the techniques shown in this course using SAS Enterprise Miner are supplemented with similar approaches in foundation SAS.

This course addresses SAS Enterprise Miner software.

Predictive Analytics and Exploratory Data Mining

• the relationship between fraud detection and exploratory data mining
• the role of graphics in exploratory analysis
• complexity in a 'PowerPoint world'
• the analyst's dilemma

Working with Unstructured Data

• data streams versus structured data
• social network analysis as a solution to unstructured problems
• statistical mechanics of network analyses
• predicting with a network
• complex networks versus reductionism
• fraud detection with social network analysis

Exploratory Data Mining and Predictive Models

• exploratory data mining success
• predictive modeling methods
• logistic regression
• decision trees
• neural networks
• the truth about neural networks
• comparing and contrasting predictive modeling methods
• model structure and impact on exploratory results
• graphical review of model results

Complex Exploratory Modeling

• initial data screening
• developing complex predictive models for exploratory efforts
• identifying important variables
• analyzing variables, domains, and clusters
• graphical review of models and data
• applying a complex predictive model to fraud detection

Exploratory Findings

• extracting new hypotheses (exploratory findings) from the predictive model
• building confidence with the exploratory findings
• recognizing and overcoming impediments to acceptance by the target audience