arXiv subjects

Matteo Fontana

Publications and source records attributed to Matteo Fontana.

23 records · Page 2Linked to original sources

arXiv2022

conformalInference.multi and conformalInference.fd: Twin Packages for Conformal Prediction

Building on top of a regression model, Conformal Prediction methods produce distribution free prediction sets, requiring only i.i.d. data. While R packages implementing such methods for the univariate response framework have been developed, this is not the case with multivariate and functional responses. conformalInference.multi and conformalInference.fd address this void, by extending classical and more advanced conformal prediction methods like full conformal, split conformal, jackknife+ and multi split conformal to deal with the multivariate and functional case. The extreme flexibility of conformal prediction, fully embraced by the structure of the package, which does not require any specific regression model, enables users to pass in any regression function as input while using basic regression models as reference. Finally, the issue of visualisation is addressed by providing embedded plotting functions to visualize prediction regions.

stat.ME↗

arXiv2021

Conformal Prediction Bands for Multivariate Functional Data

Motivated by the pressing request of methods able to create prediction sets in a general regression framework for a multivariate functional response and pushed by new methodological advancements in non-parametric prediction for functional data, we propose a set of conformal predictors that produce finite-sample either valid or exact multivariate simultaneous prediction bands under the mild assumption of exchangeable regression pairs. The fact that the prediction bands can be built around any regression estimator and that can be easily found in closed form yields a very widely usable method, which is fairly straightforward to implement. In addition, we first introduce and then describe a specific conformal predictor that guarantees an asymptotic result in terms of efficiency and inducing prediction bands able to modulate their width based on the local behavior and magnitude of the functional data. The method is investigated and analyzed through a simulation study and a real-world application in the field of urban mobility.

stat.ME↗

arXiv2021

Mobility and Economic Impact of COVID-19 Restrictions in Italy using Mobile Network Operator Data

This work presents the analysis of the impact of restrictions on mobility in Italy, with a focus on the period from 6 November 2020 to 31 January 2021, when a three-tier system based on different levels of risk was adopted and applied at regional level to contrast the second wave of COVID-19. The impact is first evaluated on mobility using Mobile Network Operator anonymised and aggregate data shared in the framework of a Business-to-Government initiative with the European Commission. Mobility data, alongside additional information about electricity consuption, are then used to assess the impacts on an economic level of the three-tier system in different areas of the country.

econ.GN↗

arXiv2021

The Importance of Being a Band: Finite-Sample Exact Distribution-Free Prediction Sets for Functional Data

Functional Data Analysis represents a field of growing interest in statistics. Despite several studies have been proposed leading to fundamental results, the problem of obtaining valid and efficient prediction sets has not been thoroughly covered. Indeed, the great majority of methods currently in the literature rely on strong distributional assumptions (e.g, Gaussianity), dimension reduction techniques and/or asymptotic arguments. In this work, we propose a new nonparametric approach in the field of Conformal Prediction based on a new family of nonconformity measures inducing conformal predictors able to create closed-form finite-sample valid or exact prediction sets under very minimal distributional assumptions. In addition, our proposal ensures that the prediction sets obtained are bands, an essential feature in the functional setting that allows the visualization and interpretation of such sets. The procedure is also fast, scalable, does not rely on functional dimension reduction techniques and allows the user to select different nonconformity measures depending on the problem at hand always obtaining valid bands. Within this family of measures, we propose also a specific measure leading to prediction bands asymptotically no less efficient than those with constant width.

stat.ME↗

arXiv2019

Multi-level conformal clustering: A distribution-free technique for clustering and anomaly detection

In this work we present a clustering technique called \textit{multi-level conformal clustering (MLCC)}. The technique is hierarchical in nature because it can be performed at multiple significance levels which yields greater insight into the data than performing it at just one level. We describe the theoretical underpinnings of MLCC, compare and contrast it with the hierarchical clustering algorithm, and then apply it to real world datasets to assess its performance. There are several advantages to using MLCC over more classical clustering techniques: Once a significance level has been set, MLCC is able to automatically select the number of clusters. Furthermore, thanks to the conformal prediction framework the resulting clustering model has a clear statistical meaning without any assumptions about the distribution of the data. This statistical robustness also allows us to perform clustering and anomaly detection simultaneously. Moreover, due to the flexibility of the conformal prediction framework, our algorithm can be used on top of many other machine learning algorithms.

stat.ML↗