Bayesian Models to Assess Risk of Corruption of Federal Management Units
Abstract
This paper presents a data mining project that generated Bayesian models to assess risk of corruption of federal management units. With thousands of extracted features related to corruptibility, the data were processed using techniques like correlation analysis and variance per class. We also compared two different discretization methods: Minimum Description Length Principle (MDLP) and Class-Attribute Contingency Coefficient (CACC). The feature selection process used Adaptive Lasso. To choose our final model we evaluated three different algorithms: Naive Bayes, Tree Augmented Naive Bayes, and Attribute Weighted Naive Bayes. Finally, we analyzed the rules generated by the model in order to support knowledge discovery.
Cite
Text
Carvalho and Carvalho. "Bayesian Models to Assess Risk of Corruption of Federal Management Units." Conference on Uncertainty in Artificial Intelligence, 2016.Markdown
[Carvalho and Carvalho. "Bayesian Models to Assess Risk of Corruption of Federal Management Units." Conference on Uncertainty in Artificial Intelligence, 2016.](https://mlanthology.org/uai/2016/carvalho2016uai-bayesian/)BibTeX
@inproceedings{carvalho2016uai-bayesian,
title = {{Bayesian Models to Assess Risk of Corruption of Federal Management Units}},
author = {Carvalho, Ricardo Silva and Carvalho, Rommel Novaes},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2016},
pages = {28-35},
url = {https://mlanthology.org/uai/2016/carvalho2016uai-bayesian/}
}