Fraudulent Democracy? An Analysis of Argentina's Infamous Decade Using Supervised Machine Learning

94 citations recorded by the source corpus.

How researchers see this paper

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

Missing Data Imputation for Supervised Learning (2016, background): “For supervised classification tasks, the objective is to fit a model on labeled training data in order to categorize new examples.”
What the Numbers Say: A Digit-Based Test for Election Fraud (2012, background): “19Note that we focus on identifying fabricated counts, not cases of ‘‘switching a proportion of votes from one party to another’’ for which Cantú and Saiegh (2011) propose their leading-digit analysis.”
Machine Learning for the Developing World (2018, methodology): “Grace et al. (2016) and Cantú and Saiegh (2011) have shown that ML can detect subtle patterns of fraud in complex data.”
An Informed Forensics Approach to Detecting Vote Irregularities (2015, methodology): “For our purposes here, the work of Cantu´ and Saiegh (2011) is particularly relevant.”