Inductive Venn-Abers Predictive Distributions: New Applications & Evaluation

Ilia Nouretdinov, James Gammerman
Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 230:490-507, 2024.

Abstract

Venn-Abers predictors offer a distribution-free probabilistic framework that generates calibrated predictions from the outputs of scoring classifiers, relying on minimal assumptions about the data distribution. This paper explores the extension of this framework from classification to regression, producing predictive distributions. We show how to evaluate the efficacy of the framework by comparing various metrics that assess the accuracy and informativeness of the predictions. We also show that the framework can be used for real-time prediction, using datasets from predictive maintenance and energy consumption forecasting.

Cite this Paper

BibTeX
@InProceedings{pmlr-v230-nouretdinov24a, title = {Inductive Venn-Abers Predictive Distributions: New Applications & Evaluation}, author = {Nouretdinov, Ilia and Gammerman, James}, booktitle = {Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {490--507}, year = {2024}, editor = {Vantini, Simone and Fontana, Matteo and Solari, Aldo and Boström, Henrik and Carlsson, Lars}, volume = {230}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v230/main/assets/nouretdinov24a/nouretdinov24a.pdf}, url = {https://proceedings.mlr.press/v230/nouretdinov24a.html}, abstract = {Venn-Abers predictors offer a distribution-free probabilistic framework that generates calibrated predictions from the outputs of scoring classifiers, relying on minimal assumptions about the data distribution. This paper explores the extension of this framework from classification to regression, producing predictive distributions. We show how to evaluate the efficacy of the framework by comparing various metrics that assess the accuracy and informativeness of the predictions. We also show that the framework can be used for real-time prediction, using datasets from predictive maintenance and energy consumption forecasting.} }
Endnote
%0 Conference Paper %T Inductive Venn-Abers Predictive Distributions: New Applications & Evaluation %A Ilia Nouretdinov %A James Gammerman %B Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2024 %E Simone Vantini %E Matteo Fontana %E Aldo Solari %E Henrik Boström %E Lars Carlsson %F pmlr-v230-nouretdinov24a %I PMLR %P 490--507 %U https://proceedings.mlr.press/v230/nouretdinov24a.html %V 230 %X Venn-Abers predictors offer a distribution-free probabilistic framework that generates calibrated predictions from the outputs of scoring classifiers, relying on minimal assumptions about the data distribution. This paper explores the extension of this framework from classification to regression, producing predictive distributions. We show how to evaluate the efficacy of the framework by comparing various metrics that assess the accuracy and informativeness of the predictions. We also show that the framework can be used for real-time prediction, using datasets from predictive maintenance and energy consumption forecasting.
APA
Nouretdinov, I. & Gammerman, J.. (2024). Inductive Venn-Abers Predictive Distributions: New Applications & Evaluation. Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 230:490-507 Available from https://proceedings.mlr.press/v230/nouretdinov24a.html.

Related Material