What is a relevant control?: an algorithmic proposal

Individualized inference (or prediction) is an approach to data analysis that is increasingly relevant thanks to the availability of large datasets. In this paper, we present an algorithm that starts by detecting the relevant observations for a given query. Further refinement of that subsample is ob...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Delbianco, Fernando, Tohmé, Fernando Abel
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2024
Materias:
Ciencias Informáticas
Individualized inference
Relevance selection
Relevance classification
Synthetic controls
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/177170
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-177170
record_format dspace
spelling I19-R120-10915-1771702025-03-07T20:07:02Z http://sedici.unlp.edu.ar/handle/10915/177170 What is a relevant control?: an algorithmic proposal Delbianco, Fernando Tohmé, Fernando Abel 2024-08 2024 2025-03-07T16:18:47Z en Ciencias Informáticas Individualized inference Relevance selection Relevance classification Synthetic controls Individualized inference (or prediction) is an approach to data analysis that is increasingly relevant thanks to the availability of large datasets. In this paper, we present an algorithm that starts by detecting the relevant observations for a given query. Further refinement of that subsample is obtained by selecting the ones with the largest Shapley values. The probability distribution over this selection allows to generate synthetic controls, which in turn can be used to generate a robust inference (or prediction). Data collected from repeating this procedure for different queries provides a deeper understanding of the general process that generates the data. Sociedad Argentina de Informática e Investigación Operativa Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 15-27
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Individualized inference
Relevance selection
Relevance classification
Synthetic controls
spellingShingle Ciencias Informáticas
Individualized inference
Relevance selection
Relevance classification
Synthetic controls
Delbianco, Fernando
Tohmé, Fernando Abel
What is a relevant control?: an algorithmic proposal
topic_facet Ciencias Informáticas
Individualized inference
Relevance selection
Relevance classification
Synthetic controls
description Individualized inference (or prediction) is an approach to data analysis that is increasingly relevant thanks to the availability of large datasets. In this paper, we present an algorithm that starts by detecting the relevant observations for a given query. Further refinement of that subsample is obtained by selecting the ones with the largest Shapley values. The probability distribution over this selection allows to generate synthetic controls, which in turn can be used to generate a robust inference (or prediction). Data collected from repeating this procedure for different queries provides a deeper understanding of the general process that generates the data.
format Objeto de conferencia
Objeto de conferencia
author Delbianco, Fernando
Tohmé, Fernando Abel
author_facet Delbianco, Fernando
Tohmé, Fernando Abel
author_sort Delbianco, Fernando
title What is a relevant control?: an algorithmic proposal
title_short What is a relevant control?: an algorithmic proposal
title_full What is a relevant control?: an algorithmic proposal
title_fullStr What is a relevant control?: an algorithmic proposal
title_full_unstemmed What is a relevant control?: an algorithmic proposal
title_sort what is a relevant control?: an algorithmic proposal
publishDate 2024
url http://sedici.unlp.edu.ar/handle/10915/177170
work_keys_str_mv AT delbiancofernando whatisarelevantcontrolanalgorithmicproposal
AT tohmefernandoabel whatisarelevantcontrolanalgorithmicproposal
_version_ 1847925346603630592

Ejemplares similares