Title

EXTRACTION OF INTERPRETABLE DECISION RULES FROM BLACK-BOX MODELS FOR CLASSIFICATION TASKS

Abstract

Abstract

In this work, we have proposed a new method and ready to use workflow to extract simplified rule sets for a given Machine Learning (ML) model trained on a classification task. Those rules are both human readable and in the form of software code pieces thanks to python programming language's syntax. We have inspired from the power of Shapley Values as our source of truth to select most prominent features for our rule sets. The aim of this work to select the key interval points in given data in order to extract if-then rule sets representing the black box models. With our work, we are able to generate rules that can mimic the ML model. End result is set of decision rules that categorizes given instances.

Supervisor(s)

Supervisor(s)

EGEMEN BERK GALATALI

Date and Location

Date and Location

2022-08-31 10:00:00

Category

Category

MSc_Thesis