Learning customized and optimized lists of rules with mathematical programming
Abstract We introduce a mathematical programming approach to building rule lists, which are a type of interpretable, nonlinear, and logical machine learning classifier involving IF-THEN rules. Unlike traditional decision tree algorithms like CART and C5.0, this method does not use gre...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Berlin Heidelberg
2021
|
| Online Access: | https://hdl.handle.net/1721.1/131392 |
| _version_ | 1811070182683049984 |
|---|---|
| author | Rudin, Cynthia Ertekin, Şeyda |
| author2 | Sloan School of Management |
| author_facet | Sloan School of Management Rudin, Cynthia Ertekin, Şeyda |
| author_sort | Rudin, Cynthia |
| collection | MIT |
| description | Abstract
We introduce a mathematical programming approach to building rule lists, which are a type of interpretable, nonlinear, and logical machine learning classifier involving IF-THEN rules. Unlike traditional decision tree algorithms like CART and C5.0, this method does not use greedy splitting and pruning. Instead, it aims to fully optimize a combination of accuracy and sparsity, obeying user-defined constraints. This method is useful for producing non-black-box predictive models, and has the benefit of a clear user-defined tradeoff between training accuracy and sparsity. The flexible framework of mathematical programming allows users to create customized models with a provable guarantee of optimality. The software reviewed as part of this submission was given the DOI (Digital Object Identifier)
https://doi.org/10.5281/zenodo.1344142
. |
| first_indexed | 2024-09-23T08:30:41Z |
| format | Article |
| id | mit-1721.1/131392 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:30:41Z |
| publishDate | 2021 |
| publisher | Springer Berlin Heidelberg |
| record_format | dspace |
| spelling | mit-1721.1/1313922023-12-14T15:38:43Z Learning customized and optimized lists of rules with mathematical programming Rudin, Cynthia Ertekin, Şeyda Sloan School of Management Abstract We introduce a mathematical programming approach to building rule lists, which are a type of interpretable, nonlinear, and logical machine learning classifier involving IF-THEN rules. Unlike traditional decision tree algorithms like CART and C5.0, this method does not use greedy splitting and pruning. Instead, it aims to fully optimize a combination of accuracy and sparsity, obeying user-defined constraints. This method is useful for producing non-black-box predictive models, and has the benefit of a clear user-defined tradeoff between training accuracy and sparsity. The flexible framework of mathematical programming allows users to create customized models with a provable guarantee of optimality. The software reviewed as part of this submission was given the DOI (Digital Object Identifier) https://doi.org/10.5281/zenodo.1344142 . 2021-09-20T17:16:53Z 2021-09-20T17:16:53Z 2018-09-05 2020-09-24T21:06:23Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/131392 en https://doi.org/10.1007/s12532-018-0143-8 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ Springer-Verlag GmbH Germany, part of Springer Nature and The Mathematical Programming Society application/pdf Springer Berlin Heidelberg Springer Berlin Heidelberg |
| spellingShingle | Rudin, Cynthia Ertekin, Şeyda Learning customized and optimized lists of rules with mathematical programming |
| title | Learning customized and optimized lists of rules with mathematical programming |
| title_full | Learning customized and optimized lists of rules with mathematical programming |
| title_fullStr | Learning customized and optimized lists of rules with mathematical programming |
| title_full_unstemmed | Learning customized and optimized lists of rules with mathematical programming |
| title_short | Learning customized and optimized lists of rules with mathematical programming |
| title_sort | learning customized and optimized lists of rules with mathematical programming |
| url | https://hdl.handle.net/1721.1/131392 |
| work_keys_str_mv | AT rudincynthia learningcustomizedandoptimizedlistsofruleswithmathematicalprogramming AT ertekinseyda learningcustomizedandoptimizedlistsofruleswithmathematicalprogramming |