The Big Data Analytics & Data Mining Program offers expertise in general data mining, pattern discovery, machine learning, and other algorithmic development for data analysis. In particular, the following core technology areas are covered:
- Association Rule Mining Techniques for discovering frequent occurring combinations of attributes, and then producing inferences based on the combinations thus discovered.
- Data Classification . Techniques for building classification models for labeled data. Typical techniques in this area are:
- Support Vector Machines
- K-nearest Neighbors
- Gaussian Mixture Models
- Data Clustering This refers to the techniques for organizing data into groups sharing similar patterns. The standard approaches for clustering include Self-organizing Map and KMeans. More advanced techniques include:
- Concurrent Clustering of Data Points and Data Attributes
- Clustering with Constraints
- Subspace Clustering
- Consulting Small scale analysis that takes a maximum of four (4) hours total to complete.
- Basic Data Analysis Analysis of basic data sets using commonly utilized bioinformatics software tools.
- Advanced Data Analysis Analysis of more complex data sets or more advanced analysis of basic data sets (includes the use of highly specialized bioinformatics software tools).
For assistance with any services and/or resources available through the Big Data Analytics & Data Mining Program, please email CCS-Data Mining.