Business Knowledge Series course

Presented by Jared Dean, Distinguished Software Developer, SAS

This course introduces the concepts of analytical computing and various data mining concepts, including predictive modeling. The course introduces a wide array of topics including the key elements of modern computing environments, an introduction to data mining algorithms, segmentation, data mining methodology, time-series data mining, text mining, and more. Throughout the course, concepts are introduced, explained, and demonstrated using approachable real-world examples. The instructor will share his extensive experience from consulting with clients on their analytic efforts as well as from his own projects throughout his career.

This course is not hands-on training for SAS Enterprise Miner software, although SAS Enterprise Miner is used by the instructor to illustrate specific modeling techniques and by students for their classroom exercises.

Learn how to

• use a data mining methodology
• apply modern cutting-edge algorithms to data
• implement best practices in the development and maintaining of analytical models
• explore the opportunities to create value through analytics
• assess different machine-learning models
• explain in simple terms model data mining and machine-learning methods
• incorporate unstructured data into your business models and decisions
• build segments for business applications.

Who should attend

Business analysts, statisticians, data scientists, their managers, and anyone who wants to understand what is analytics and how analytics can benefit their business

Formats available	Duration
Classroom:	14.0 hours

No previous courses are required. It is recommended that you have a basic working knowledge of analytics and/or statistics, and familiarity with the SAS language is a plus.

This course addresses SAS Enterprise Miner, SAS Text Miner software.

The Computing Environment

• hardware
• storage (disk)
• central processing unit
• memory
• network
• distributed systems: database computing and file system computing
• virtualization

Analytical Tools

• exercise: inventory of tools

Overview of Segmentation Ideas and Techniques

• segmentation
• cluster analysis
• distance measures (metrics)
• evaluating clustering
• number of clusters
• K-means algorithm
• hierarchical clustering
• profiling clusters

Predictive Modeling

• a methodology for building models
• SEMMA
• model types: binary classification, multilevel classification, and interval prediction
• assessment of predictive models
• common predictive modeling techniques
• RFM
• contrast predictive modeling from segmentation

Common Predictive Modeling Techniques

• regression
• generalized linear models
• neural networks
• decision and regression trees

Special Applications

• incremental response modeling: building the response model and measuring the incremental response
• time series data mining
• recommendation systems
• text analytics: information retrieval and content categorization
• text mining