---
title: "Toward a Probabilistic Formalization of Case-Based Inference"
authors:
  - "Eyke Hüllermeier"
doi: ""
url: "https://ijcai.org/proceedings/1999/37"
pdf: "https://ijcai.org/proceedings/1999/0037.pdf"
venue: "Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence"
year: 1999
pages: "248-252"
track: "Case-based Reasoning"
keywords:
---

# Toward a Probabilistic Formalization of Case-Based Inference

Eyke Hüllermeier

*Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence*, pages 248-252.

## Abstract

We propose a formal framework for modelling case-based inference (CBI), which is a crucial part of the case-based reasoning (CBR) methodology. As a representation of the similarity structure of a system, the concept of a similarity profile is introduced. This concept makes it possible to formalize the <?Bhypothesis that "similar problems have similar solutions" and to realize CBI in the form of constraint-based inference. In order to exploit the similarity structure more efficie~tly, a probabilistic generalization of the constramtbased view is developed. This formalization allows for realizing CBI in the context of probabilistic reasoning and statistical inference and, hence, makes a powerful methodological framework accessible to CBR. Within the generalized setting, a (formalized) CBR hypothesis corresponds to the assumption of a certain stochastic model, and a memory of cases can be seen as statistical data underlying the inference process. As a particular result we establish an approximate probabilistic reasoning scheme which generalizes the constraint-based approach.