Machine-learned models are often perceived as "black boxes": they are given inputs and hopefully produce desired outputs. There are many circumstances, however, where human-interpretability is crucial to understand (i) why a model outputs a certain prediction on a given instance, (ii) which adjustable features of that instance should be modified, and finally (iii) how to alter a prediction when the mutated instance is input back to the model. In this paper, we present a technique that exploits the feedback loop originated from the internals of any ensemble of decision trees to offer recommendations for transforming a k-labelled predicted instance into a k'-labelled one (for any possible pair of class labels k, k'). Our proposed algorithm perturbs individual feature values of an instance, so as to change the original prediction output by the ensemble on the so-transformed instance. This is also achieved under two constraints: the cost and tolerance of transformation. Finally, we evaluate our approach on four distinct application domains: online advertising, healthcare, spam filtering, and handwritten digit recognition. Experiments confirm that our solution is able to suggest changes to feature values that help interpreting the rationale of model predictions, making it indeed useful in practice especially if implemented efficiently.

Generating actionable interpretations from ensembles of decision trees / Tolomei, Gabriele; Silvestri, Fabrizio. - In: IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING. - ISSN 1041-4347. - 33:4(2021), pp. 1540-1553. [10.1109/TKDE.2019.2945326]

Generating actionable interpretations from ensembles of decision trees

Tolomei, Gabriele
;
Silvestri, Fabrizio
2021

Abstract

Machine-learned models are often perceived as "black boxes": they are given inputs and hopefully produce desired outputs. There are many circumstances, however, where human-interpretability is crucial to understand (i) why a model outputs a certain prediction on a given instance, (ii) which adjustable features of that instance should be modified, and finally (iii) how to alter a prediction when the mutated instance is input back to the model. In this paper, we present a technique that exploits the feedback loop originated from the internals of any ensemble of decision trees to offer recommendations for transforming a k-labelled predicted instance into a k'-labelled one (for any possible pair of class labels k, k'). Our proposed algorithm perturbs individual feature values of an instance, so as to change the original prediction output by the ensemble on the so-transformed instance. This is also achieved under two constraints: the cost and tolerance of transformation. Finally, we evaluate our approach on four distinct application domains: online advertising, healthcare, spam filtering, and handwritten digit recognition. Experiments confirm that our solution is able to suggest changes to feature values that help interpreting the rationale of model predictions, making it indeed useful in practice especially if implemented efficiently.
2021
machine learning interpretability; actionable feature tweaking; recommending feature changes; altering model predictions; ensemble of decision trees
01 Pubblicazione su rivista::01a Articolo in rivista
Generating actionable interpretations from ensembles of decision trees / Tolomei, Gabriele; Silvestri, Fabrizio. - In: IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING. - ISSN 1041-4347. - 33:4(2021), pp. 1540-1553. [10.1109/TKDE.2019.2945326]
File allegati a questo prodotto
File Dimensione Formato  
Tolomei_postprint_generating_2019.pdf

accesso aperto

Note: DOI: 10.1109/TKDE.2019.2945326
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.29 MB
Formato Adobe PDF
3.29 MB Adobe PDF
Tolomei_generating_2021.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.36 MB
Formato Adobe PDF
2.36 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1338769
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 7
social impact