Case-Based Predictions: An Axiomatic Approach to Prediction, Classification and Statistical Learning

Abstract : The book presents an axiomatic approach to the problems of prediction, classification, and statistical learning. Using methodologies from axiomatic decision theory, and, in particular, the authors' case-based decision theory, the present studies attempt to ask what inductive conclusions can be derived from existing databases. It is shown that simple consistency rules lead to similarity-weighted aggregation, akin to kernel-based methods. It is suggested that the similarity function be estimated from the data. The incorporation of rule-based reasoning is discussed.
Type de document :
Ouvrage (y compris édition critique et traduction)
World Scientific Publishers, pp.NC, 2011, Economic Theory Series
Liste complète des métadonnées

https://hal-hec.archives-ouvertes.fr/hal-00756301
Contributeur : Amaury Bouvet <>
Soumis le : jeudi 22 novembre 2012 - 17:07:29
Dernière modification le : jeudi 11 janvier 2018 - 06:19:31

Identifiants

  • HAL Id : hal-00756301, version 1

Collections

Citation

Itzhak Gilboa, David Schmeidler. Case-Based Predictions: An Axiomatic Approach to Prediction, Classification and Statistical Learning. World Scientific Publishers, pp.NC, 2011, Economic Theory Series. 〈hal-00756301〉

Partager

Métriques

Consultations de la notice

203