Document - Explaining crash predictions on multivariate time series data

2022

Conference article Open Access

Explaining crash predictions on multivariate time series data

Spinnato F., Guidotti R., Nanni M., Maccagnola D., Paciello G., Farina A. B.

Case study Multivariate time series Car insurance Crash prediction Interpretable machine learning Explainability

In Assicurazioni Generali, an automatic decision-making model is used to check real-time multivariate time series and alert if a car crash happened. In such a way, a Generali operator can call the customer to provide first assistance. The high sensitivity of the model used, combined with the fact that the model is not interpretable, might cause the operator to call customers even though a car crash did not happen but only due to a harsh deviation or the fact that the road is bumpy. Our goal is to tackle the problem of interpretability for car crash prediction and propose an eXplainable Artificial Intelligence (XAI) workflow that allows gaining insights regarding the logic behind the deep learning predictive model adopted by Generali. We reach our goal by building an interpretable alternative to the current obscure model that also reduces the training data usage and the prediction time.

Source: DS 2022 - 25th International Conference on Discovery Science, pp. 556–566, Montpellier, France, 10-12/10/2022

Publisher: Springer, Berlin , Germania

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:it.cnr:prodotti:477662,
	title = {Explaining crash predictions on multivariate time series data},
	author = {Spinnato F. and Guidotti R. and Nanni M. and Maccagnola D. and Paciello G. and Farina A. B.},
	publisher = {Springer, Berlin , Germania},
	doi = {10.1007/978-3-031-18840-4_39},
	booktitle = {DS 2022 - 25th International Conference on Discovery Science, pp. 556–566, Montpellier, France, 10-12/10/2022},
	year = {2022}
}