Data-Driven Investigative Journalism For Connectas Dataset

TL;DR

This paper demonstrates how machine learning can be applied to analyze government contract data in Colombia to identify corruption and malpractice, involving data cleaning, feature engineering, and anomaly detection models.

Contribution

It introduces a methodology for applying machine learning to corruption detection in government datasets, including data preprocessing and anomaly detection techniques.

Findings

Effective data cleaning and feature engineering for government contract data

Successful implementation of anomaly detection models

Potential to assist in corruption investigations

Abstract

The following paper explores the possibility of using Machine Learning algorithms to detect the cases of corruption and malpractice by governments. The dataset used by the authors contains information about several government contracts in Colombia from year 2007 to 2012. The authors begin with exploring and cleaning the data, followed by which they perform feature engineering before finally implementing Machine Learning models to detect anomalies in the given dataset.