The goal of this work is to organize, extract and present relevant information contained in a variety of real-world data sets.
The work requires familiarity with efficient data manipulation techniques, as well as various data mining and machine learning methods applied to big data such as data with large volume, high velocity, high variability and changing definitions.
Projects in this area may focus on:
- Assessing the suitability of existing methods for the application problem being targeted, with articulation of potential inadequacies in these methods.
- Formulating and developing new methods or modifications of existing methods aimed primarily at the target problem, but also suitable for more general use.
- Developing software and visualization modes of presentation and interaction for transparency of the algorithms for users.