Description:

SLIM is new machine learning method for building data-driven scoring systems -- that is, simple classification models that let users make quick predictions by adding, subtracting and multiplying a few small numbers.

slim for matlab is a package to create scoring systems that are fully optimized for accuracy and sparsity, and that satisfy difficult constraints without parameter tuning (e.g. hard limits on model size, the true positive rate, the false positive rate).

This package requires MATLAB (2014b+) and the IBM CPLEX Optimization Studio (v12.6 or later).

Changes to previous version:

Initial Announcement on mloss.org.

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Linux, Windows, Unix, Mac, Osx

Data Formats: Matlab

Tags: Classification, Optimization, Sparsity, Constraints, Integer Programming, Scoring Systems, Simple

Archive: download here

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.