Code

Series Finder
(code) | (paper)

For detecting crime series.

Actionable and Interpretable Treatment Regimes (CITR)
(code) | (paper)

For creating a policy. Uses causal inference, includes costs of gathering information, treatment, and effectiveness of the treatment.

Certifiably Optimal RulE ListS (CORELS)
(code) | (paper)

For classification, an alternative to decision trees. Non-probabilistic, but with proof of optimality.

Learning Optimized Risk Scores from Large-Scale Datasets (RiskSLIM)
(code) | (paper)

Creates risk assessment scoring systems.

ClusteR-specific Assorted Feature selecTion (CRAFT)
(code) | (paper)

Clustering with cluster-specific feature selection.

Scalable Bayesian Rule Lists (SBRL)
(R interface, C code - Creative Commons License) | (paper) | (bib)

For classification, an alternative to decision trees. Faster than BRL.

Bayesian Case Model (BCM)
(code) | (paper)

Prototype clustering with cluster-specific feature selection.

Box Drawings for Learning with Imbalanced Data
(matlab code) | (paper) | (bib)

For imbalanced classification with real-valued features.

Bayesian Rule Lists (BRL)
(python code - MIT license) | (paper) | (bib)

For classification, an alternative to decision trees.

Bayesian Or's of And's
(code) | (paper) | (bib)

For classification, an alternative to decision trees, inductive logic programming and associative classification.

Supersparse Linear Integer Models (SLIM)
(matlab code) | (python code) | (paper) | (bib)

For building scoring systems, which are linear models with integer coefficients. Part of winning entry for 2016 INFORMS Innovative Applications in Analytics Award.

Falling Rule Lists (FRL)
(python code) | (paper) | (bib)

For classification where the probabilities decrease along the list.

Growing a List
(python code) | (paper) | (bib)

A search engine that performs set expansion. Note that this code is artificially slowed down by a restriction on the number of queries per minute, imposed by search engine companies. Unrestricted access to a search engine would eliminate this issue.

On Combining Machine Learning with Decision Making
(code) | (paper) | (bib)

For new decision making framework.