Electoral Intelligence: A Neural Zero-Inflated Negative Binomial Model for Forecasting Swedish Municipal Elections
Abstract
Forecasting local elections is difficult because electoral competition is geographically heterogeneous, highly overdispersed, and characterized by many party-municipality combinations with little or no electoral activity. This article develops a bounded neural zero-inflated negative binomial (ZINB) model for forecasting party-level vote counts in Swedish municipal elections. The model combines a count component for expected votes, a zero-inflation component for structural electoral absence, municipality-specific dispersion, and learned embeddings capturing latent party, municipality, and party-municipality structure. Model training relies on data from the 2014, 2018, and 2022 Swedish municipal elections and performance is evaluated on a held-out set of municipalities. Testing results show strong predictive accuracy in both vote counts and vote shares. Explanatory diagnostics indicate that latent party structure, local party-municipality relationships, electoral persistence, organizational capacity, and candidate-electorate representational similarity are among the most important determinants of predictive performance. Following model evaluation and diagnostics, the selected specification is refit on all historical data and applied to generate forecasts for the 2026 municipal elections. The proposed framework provides a flexible approach for studying local electoral competition in multiparty systems characterized by heterogeneous party presence and substantial geographic variation.
Related
- An autocomplete model for elections
- The Deterministic Hare Core Is Nonempty for Nine-Seat Approval Elections
- Probabilistic Quantification of Swing State Importance in the 2024 Electoral College
- A Dynamic Model of Party Differentiation under Electoral Competition
- Objective Bayes Factor Based Model Selection for Zero-Inflated Microbiome Count Data Under Jeffreys Prior
BibTeX
@misc{qi2026electoral,
title = {{Electoral Intelligence: A Neural Zero-Inflated Negative Binomial Model for Forecasting Swedish Municipal Elections}},
author = {Haodong Qi and Stefano M. Iacus and Pieter Bevelander and Derek S. Hutcheson},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.08501},
eprint = {2611.08501},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.08501},
}
RIS
TY - UNPB
TI - Electoral Intelligence: A Neural Zero-Inflated Negative Binomial Model for Forecasting Swedish Municipal Elections
AU - Haodong Qi
AU - Stefano M. Iacus
AU - Pieter Bevelander
AU - Derek S. Hutcheson
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.08501
UR - https://arxiv.org/abs/2611.08501
AB - Forecasting local elections is difficult because electoral competition is geographically heterogeneous, highly overdispersed, and characterized by many party-municipality combinations with little or no electoral activity. This article develops a bounded neural zero-inflated negative binomial (ZINB) model for forecasting party-level vote counts in Swedish municipal elections. The model combines a count component for expected votes, a zero-inflation component for structural electoral absence, municipality-specific dispersion, and learned embeddings capturing latent party, municipality, and party-municipality structure. Model training relies on data from the 2014, 2018, and 2022 Swedish municipal elections and performance is evaluated on a held-out set of municipalities. Testing results show strong predictive accuracy in both vote counts and vote shares. Explanatory diagnostics indicate that latent party structure, local party-municipality relationships, electoral persistence, organizational capacity, and candidate-electorate representational similarity are among the most important determinants of predictive performance. Following model evaluation and diagnostics, the selected specification is refit on all historical data and applied to generate forecasts for the 2026 municipal elections. The proposed framework provides a flexible approach for studying local electoral competition in multiparty systems characterized by heterogeneous party presence and substantial geographic variation.
ER -