Log-linear analysis is the statistical method used to capture multi-way relationships between variables. However, due to its exponential nature, previous approaches did not allow scale-up to more than a dozen variables.
We present here Chordalysis, a log-linear analysis method for big data. Chordalysis exploits recent discoveries in graph theory by representing complex models as compositions of triangular structures, also known as chordal graphs. Chordalysis makes it possible to discover the structure of datasets with hundreds of variables on a standard desktop computer.
This method has been presented at the IEEE International Conference on Data Mining 2013.
Details can be found in the associated paper:
YourKit is supporting Chordalysis open source project with its full-featured Java Profiler.
YourKit is the creator of innovative and intelligent tools for profiling Java and .NET applications. http://www.yourkit.com
- Reveals the structure of high-dimensional data
- Log-linear analysis for high-dimensional data
Be the first to post a review of Chordalysis!