Our Work
What do we do?
Need to understand the behavior of random walks on your graph? Not sure if you should use PageRank, SALSA, DISCO, or the myriad of other recommendation and similarity computation algorithms out there? We can help.
Are your finite difference/element/volume simulations blowing up? Having trouble figuring out the right way to impose those pesky boundary conditions? We can help.
Need to solve really big linear systems? Looking for the best way to compute the eigenvalues of your matrix? We can help.
Past projects C² consultants have completed include:
- Improved Twitter's link recommendation engine follow rate by 50% using binary classification and supervised random walks.
- Improved Phillips MRI scanning rates by 4x with higher image quality using compressed sensing.
- Improved statistical machine translation engine for documents written in less-common languages.
- Created the Obama 2012 campaign model for identifying likely donors by connecting social networks to political and demographic datasets.
- Detected off-label drug usage using millions of doctors' notes from Stanford Hospital and other outpatient facilities and developed a tool to extract structured information about problems, medications, and procedures from the resulting unstructured text.
Furthermore, several of our members are from the Stanford Systems Optimization Laboratory, which produces optimization software that has been applied in many areas of engineering, economics, finance, forestry, etc. Some examples include:
- Design of both yachts in the 1995 America's Cup final
- Online control of transmission networks for electricity and gas
- Prediction of oil prices by the Federal Reserve
- Climate modeling for the greenhouse debate
- Determination of forces on the thigh bone prior to prosthesis insertion
- Trajectory optimization for aircraft and spacecraft (including optimal control of the DC-X experimental single-stage VTOL rocket)