Neural networks would 'vote' according to Borda's rule

David Burka, Clemens Puppe (), Laszlo Szepesvary and Attila Tasnádi

No 96, Working Paper Series in Economics from Karlsruhe Institute of Technology (KIT), Department of Economics and Management

Abstract: Can neural networks learn to select an alternative based on a systematic aggregation of conflicting individual preferences (i.e. a 'voting rule')? And if so, which voting rule best describes their behavior? We show that a prominent neural network can be trained to respect two fundamental principles of voting theory, the unanimity principle and the Pareto property. Building on this positive result, we train the neural network on profiles of ballots possessing a Condorcet winner, a unique Borda winner, and a unique plurality winner, respectively. We investigate which social outcome the trained neural network chooses, and find that among a number of popular voting rules its behavior mimics most closely the Borda rule. Indeed, the neural network chooses the Borda winner most often, no matter on which voting rule it was trained. Neural networks thus seem to give a surprisingly clear-cut answer to one of the most fundamental and controversial problems in voting theory: the determination of the most salient election method.

Keywords: voting; social choice; neural networks; machine learning; Borda count (search for similar items in EconPapers)
Date: 2016
New Economics Papers: this item is included in nep-pol
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/147982/1/872322491.pdf (application/pdf)

Related works:
Working Paper: Neural networks would 'vote' according to Borda's Rule (2016)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:kitwps:96

DOI: 10.5445/IR/1000062014

Access Statistics for this paper

More papers in Working Paper Series in Economics from Karlsruhe Institute of Technology (KIT), Department of Economics and Management Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().