Technology advancements now allow companies to capture and store large amount of data (or facts)
in databases and data warehouses. With so much raw data, organizations urgently need tools
that allow them to effectively sift through these enormous datasets and extract
actionable information and knowledge (meaningful patterns, trends, and anomalies) from
such data sets to help them optimize businesses. Predictive modeling is the process of
developing models to better predict future outcomes for an event of interest by exploring
its relationships with explanatory variables from historical data. It is used extensively
in businesses to identify risks and opportunities associated with a set of conditions.
The course introduces the techniques of predictive modeling and analytics
in a data‐rich business environment. It covers the process of formulating business objectives,
data selection, preparation, and partition to successfully design, build, evaluate and
implement predictive models for a variety of practical business applications (such as
direct marketing, cross selling, customer retention, delinquency and collection analytics,
fraud detection, machine failure detection, insurance underwriting). Predictive models
such as classification and decision trees, neural networks, regressions, association analysis,
link analysis, and others will be studied. It is practically oriented with a focus of
applying data analytic tools to help companies answer business questions such as who is
likely to respond to a new advertisement, what customers are most likely to be default
on a loan/payment, what transactions are most likely to be fraudulent, and what combinations
of products are customers most likely to purchase at the same time.
The primary approach will entail ‘learning-by-doing’ with the use of the state-of-the-art software
such as SAS JMP®, SAS Enterprise Miner®, and a variety of open source software.
Course includes: Data Visualization; Predictive Models; Model Assessment, Scoring and Implementation