Decision making in the TBM: the necessity of the pignistic transformation

By Philippe Smets. International Journal of Approximate Reasoning, 2005

707 citations recorded by the source corpus.

In the transferable belief model (TBM), pignistic probabilities are used for decision making. The nature of the pignistic transformation is justified by a linearity requirement. We justify the origin of this requirement showing it is not ad hoc but unavoidable provides one accepts expected utility theory.

Subfields: Artificial Intelligence, General Decision Sciences, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/e91498ce94e297640caea3f3938c43734d039093

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Michel Verleysen
2. Benoît Frénay
3. Weiru Liu
4. Thierry Denoeux
5. Marie-Hélène Masson
6. Robi Polikar
7. Jacob Goldberger
8. P. Shanti Sastry

In General Decision Sciences

1. Weiru Liu
2. Thierry Denoeux
3. Michel Verleysen
4. Benoît Frénay
5. Marie-Hélène Masson

In Management Science and Operations Research

1. Weiru Liu
2. Thierry Denoeux
3. Michel Verleysen
4. Benoît Frénay
5. Marie-Hélène Masson

Citations in the corpus

• Analyzing the degree of conflict among belief functions (2006, background): “When m(A) > 0, A is called a focal element of the belief function.”
• Classification in the Presence of Label Noise: A Survey (2014, background): “Notice that Smets [266] argues that it is necessary to fall back to classical probabilities to make decisions.”
• ECM: An evidential version of the fuzzy c (2008, background): “He has shown that the only transformation of a belief function into a probability function satisfying elementary rationality requirements is the pignistic transformation, in which each mass of belief m(A) is equally distributed among the elements of A [32].”