Learning Real-Life Approval Elections

TL;DR

This paper introduces algorithms to learn independent approval models from election data, demonstrating that mixtures of models better capture real-world approval election complexities.

Contribution

It develops novel algorithms for learning IAMs and their mixtures from data, extending previous models and applying them to real election datasets.

Findings

Single-component models are often insufficient for real data

Mixture models provide a better fit to real-life approval elections

Algorithms successfully applied to Pabulib database

Abstract

We study the independent approval model (IAM) for approval elections, where each candidate has its own approval probability and is approved independently of the other ones. This model generalizes, e.g., the impartial culture, the Hamming noise model, and the resampling model. We propose algorithms for learning IAMs and their mixtures from data, using either maximum likelihood estimation or Bayesian learning. We then apply these algorithms to a large set of elections from the Pabulib database. In particular, we find that single-component models are rarely sufficient to capture the complexity of real-life data, whereas their mixtures perform well.