Rapporto tecnico, 2018, ENG

Assessing the stability of interpretable models

Guidotti R.; Ruggieri S.

CNR-ISTI, Pisa, Italy; Università di Pisa, Pisa, Italy and CNR-ISTI, Pisa, Italy

Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or a linear model, are widely recognized as human-interpretable. However, such models are generated as part of a larger analytical process, which, in particular, comprises data collection and filtering. Selection bias in data collection or in data pre-processing may affect the model learned. Although model induction algorithms are designed to learn to generalize, they pursue optimization of predictive accuracy. It remains unclear how interpretability is instead impacted. We conduct an experimental analysis to investigate whether interpretable models are able to cope with data selection bias as far as interpretability is concerned.

Keywords

Interpretable models, Stability, Overfitting

CNR authors

Ruggieri Salvatore, Guidotti Riccardo

CNR institutes

ISTI – Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"

ID: 397161

Year: 2018

Type: Rapporto tecnico

Creation: 2019-01-02 10:18:21.000

Last update: 2020-12-18 19:36:13.000

External links

OAI-PMH: Dublin Core

OAI-PMH: Mods

OAI-PMH: RDF

URL: https://arxiv.org/pdf/1810.09352.pdf

External IDs

CNR OAI-PMH: oai:it.cnr:prodotti:397161