Reliable Household Demographic Classification

Javier Carreno, Khuong An Nguyen, Zhiyuan Luo, Andrew Fish
Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 266:753-755, 2025.

Abstract

We propose the Hybrid Calibration Score (HCS), a new nonconformity measure for inductive conformal prediction. HCS combines instance-level scoring with global model calibration via Expected Calibration Error. On a real-world demographic classification task, HCS achieves 99% coverage with smaller prediction sets (APS = 1.55) and higher decisiveness (OneC = 55.19%) than standard measures, while preserving formal coverage guarantees.

Cite this Paper

BibTeX
@InProceedings{pmlr-v266-carreno25a, title = {Reliable Household Demographic Classification}, author = {Carreno, Javier and Nguyen, Khuong An and Luo, Zhiyuan and Fish, Andrew}, booktitle = {Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {753--755}, year = {2025}, editor = {Nguyen, Khuong An and Luo, Zhiyuan and Papadopoulos, Harris and Löfström, Tuwe and Carlsson, Lars and Boström, Henrik}, volume = {266}, series = {Proceedings of Machine Learning Research}, month = {10--12 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v266/main/assets/carreno25a/carreno25a.pdf}, url = {https://proceedings.mlr.press/v266/carreno25a.html}, abstract = {We propose the Hybrid Calibration Score (HCS), a new nonconformity measure for inductive conformal prediction. HCS combines instance-level scoring with global model calibration via Expected Calibration Error. On a real-world demographic classification task, HCS achieves 99% coverage with smaller prediction sets (APS = 1.55) and higher decisiveness (OneC = 55.19%) than standard measures, while preserving formal coverage guarantees.} }
Endnote
%0 Conference Paper %T Reliable Household Demographic Classification %A Javier Carreno %A Khuong An Nguyen %A Zhiyuan Luo %A Andrew Fish %B Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2025 %E Khuong An Nguyen %E Zhiyuan Luo %E Harris Papadopoulos %E Tuwe Löfström %E Lars Carlsson %E Henrik Boström %F pmlr-v266-carreno25a %I PMLR %P 753--755 %U https://proceedings.mlr.press/v266/carreno25a.html %V 266 %X We propose the Hybrid Calibration Score (HCS), a new nonconformity measure for inductive conformal prediction. HCS combines instance-level scoring with global model calibration via Expected Calibration Error. On a real-world demographic classification task, HCS achieves 99% coverage with smaller prediction sets (APS = 1.55) and higher decisiveness (OneC = 55.19%) than standard measures, while preserving formal coverage guarantees.
APA
Carreno, J., Nguyen, K.A., Luo, Z. & Fish, A.. (2025). Reliable Household Demographic Classification. Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 266:753-755 Available from https://proceedings.mlr.press/v266/carreno25a.html.

Related Material