Efficient Analysis of Large Data Sets

Catalog description

This course introduces methods to make analysis of large data sets efficient. The course centers on several key ideas for efficient data analysis and shows how those ideas manifest in different scenarios, characterized by data, task, and hardware properties. For instance, the course covers topics such as creating data structures to optimally support specific analysis goals, efficient implementation of atomic operators, scheduling and analysis process optimization, approximate processing, and caching strategies. The course builds on the CS 4320 /5320 course (Introduction to Database Systems), introducing students to efficient data analysis in the context of relational database systems. It expands over the introductory content by discussing advanced analysis methods and broadening the scope from relational database systems to various other types of analysis scenarios.