FPS: FAQ: Frequently Asked Questions

1. What is FPS?
2. Who should use FPS?
3. What functions does FPS provide?
4. What do I need in order to run FPS?
5. What can I do as a developer?
6. My question isn't answered here. Whom should I ask?

1. What is FPS?
   
   FPS (Fast Prediction via Sparsity) is a high performance tool that predicts the future values of a time series based on sparse correlations between this time series and other time series in a real-time environment.
   
   
2. Who should use FPS?
   
   People who require real-time prediction over one or many time series.
   
   
3. What functions does FPS provide?
   
   FPS provide a Matlab object IncrementalPredict.m that can do real-time predictions on a particular series based on other series and itself. FPS also provides a Matlab function train_model.m that, given a training data and sets of parameters, return the parameters that are likely to produce more profits in the test data than other parameters among all the given parameters.
   
   
4. What do I need in order to run FPS?
   
   FPS is built in Matlab, so it can run on Windows/Unix/Linux .
   To run FPS, Matlab is necessary. Users can buy it from here.
   
   
5. What can I do as a developer?
   
   In the software package, two files IncrementalPredict.m and train_model.m are included. A developer can easily integrate these two files into his or her Matlab project. People can find a sample usage of train_model.m and IncrementalPredict.m in sample_run.m. All the codes are fully documented and thus easy to follow. Any questions or feedbacks are welcome.
   
   
6. My question isn't answered here. Whom should I ask?
   
   You can send email to shasha@cs.nyu.edu or jjx203@cs.nyu.edu to contact the authors of the software.
   

Maintained by jjx203@cs.nyu.edu

Last Updated Dec 17th, 2009