Generating Actionable Interpretations from Ensembles of Decision Trees
| Autor: | Fabrizio Silvestri, Gabriele Tolomei |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Class (computer programming)
Theoretical computer science Computer science Decision tree 02 engineering and technology Feedback loop Prime (order theory) machine learning interpretability actionable feature tweaking recommending feature changes altering model predictions ensemble of decision trees Computer Science Applications Transformation (function) Computational Theory and Mathematics Handwriting recognition 020204 information systems 0202 electrical engineering electronic engineering information engineering Feature (machine learning) Task analysis Information Systems |
| Zdroj: | IEEE Transactions on Knowledge and Data Engineering. 33:1540-1553 |
| ISSN: | 2326-3865 1041-4347 |
| Popis: | 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 $k$ k -labelled predicted instance into a $k^{\prime }$ k ' -labelled one (for any possible pair of class labels $k$ k , $k^{\prime }$ 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|