Big Data Analytics

Students learn and apply techniques for inference and discovery in large data sets. Topics include statistical inference, exploratory data analysis, data mining, text mining, and machine learning for predictive modeling.

Large-scale enterprise systems often rely on architectural frameworks that define their main components as well as the interactions among these components. Students in this course survey the principal design strategies and tools for constructing the modern information system. They identify common vendor and open-source components, illustrating how these elements can create and integrate robust web- and cloud-based services and applications.

Statistical analysis supports quality management, drives decision making, enables forecasting and prediction, and provides a means for understanding many aspects of our world. Data is everywhere in today's integrated technological society, and statistical analysis provides the means to access and interpret data. Students in this course are introduced to statistics focused on working with complex data sets and analyzing big data. Students synthesize theory with practical applications to learn the fundamentals of statistical reasoning, descriptive statistics, visual data display, regression, hypothesis testing, research design, anomaly detection, and advanced analysis practices. They have the opportunity to practice using a statistical software package to solve statistical problems. Students use a publicly available big data set to formulate their own study and complete a statistical analysis.

The amount of data available to organizations to help them create a competitive advantage is growing exponentially. These data sets are so large and complex that traditional data modeling and data analysis processes are inadequate. In this course, students are guided through basic approaches to querying and exploring data using higher level tools built on top of a Hadoop Platform. Students will walk through query interfaces, environments, and the canonical situations for tools like HBASE, HIVE, Pig, as well as more open source tools like HUE.

Big Data normally refers to petabytes (1000 terabytes) or exabytes (one billion gigabytes) of unstructured data. This amount of data requires new methods to analyze, visualize, and present these data in a way that yields insight and understanding. Students in this course are introduced to elementary graphics programming, focusing primarily on two-dimensional vector graphics and the programming platforms for graphics. This infrastructure will also include lessons on the human side of visualization, studying human perception and cognition to gain a better understanding of the target of the data visualization.