Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Predicting irregularities in public bidding: an application of neural networks
Search
Thiago Marzagão
May 28, 2017
Research
0
3k
Predicting irregularities in public bidding: an application of neural networks
Thiago Marzagão
May 28, 2017
Tweet
Share
More Decks by Thiago Marzagão
See All by Thiago Marzagão
Aula inagural na ENAP
thiagomarzagao
0
810
SICSS presentation
thiagomarzagao
0
780
antitrust uses and misuses (in the age of Big Data)
thiagomarzagao
1
1.7k
mineração de dados
thiagomarzagao
0
2.4k
mineração de dados no governo
thiagomarzagao
1
2.9k
Using AI to fight corruption in the Brazilian government
thiagomarzagao
0
240
Uso de Técnicas de Mineração de Dados no Monitoramento dos Gastos Públicos e no Combate à Corrupção
thiagomarzagao
0
2.9k
Mineração de Dados no Governo Federal
thiagomarzagao
0
110
Classificação Automatizada de Produtos e Serviços Licitados
thiagomarzagao
0
72
Other Decks in Research
See All in Research
SANER 2019 Most Influential Paper Talk
tsantalis
0
120
Deep State Space Models 101 / Mamba
kurita
9
3.5k
待機電力を削減したネットワーク更新型電子ペーパーサイネージの開発と評価 / IOT64
yumulab
0
100
Embodied AIについて / About Embodied AI
nttcom
1
540
[Human-AI Decision Making勉強会] 説明の更新はユーザにどのような影響をもたらすか
okoso
1
170
論文紹介 DSRNet: Single Image Reflection Separation via Component Synergy (ICCV 2023)
tattaka
0
180
「EBPMエコシステム」の可能性
daimoriwaki
0
200
CSC590 Lecture 01
javiergs
PRO
0
130
CVPR2023 EarthVision Workshopより衛星画像関連論文紹介 / Satellite Imaging Processing Papers in CVPR2023 EarthVision Workshop
nttcom
0
120
People Driven Transformation / 人が起点の、社会の変え方
dmattsun
0
150
Alternative Photographic Processes Reimagined: The Role of Digital Technology in Revitalizing Classic Printing Techniques【SIGGRAPH Asia 2023】
toremolo72
0
430
LiDARセキュリティ最前線
kentaroy47
0
280
Featured
See All Featured
In The Pink: A Labor of Love
frogandcode
138
21k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
60
14k
The Language of Interfaces
destraynor
151
23k
The Mythical Team-Month
searls
216
42k
StorybookのUI Testing Handbookを読んだ
zakiyama
13
4.6k
ParisWeb 2013: Learning to Love: Crash Course in Emotional UX Design
dotmariusz
104
6.6k
The Brand Is Dead. Long Live the Brand.
mthomps
49
28k
Done Done
chrislema
178
15k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
6
1.5k
Writing Fast Ruby
sferik
621
60k
jQuery: Nuts, Bolts and Bling
dougneiner
59
7.1k
A designer walks into a library…
pauljervisheath
200
23k
Transcript
Predicting irregularities in public bidding: an application of neural networks
Observatory of Public Spending
Government contractor doesn’t pay employees Default epidemy in the federal
government: 4 companies went bankrupt Construction company abandons 3 projects Observatory of Public Spending
Observatory of Public Spending what if we could predict which
contractors will become headaches?
Observatory of Public Spending
Observatory of Public Spending impossible to do manually ~25k new
contracts every year
Observatory of Public Spending
Observatory of Public Spending data + neural networks = predictions
Observatory of Public Spending data: - n = 10186 -
9442 (~93%) not problem - 744 (~ 7%) problem - 2011-2016
Observatory of Public Spending data: - Y: has the company
been punished before?
Observatory of Public Spending data: - X: a total of
183 attributes, like: - # of employees - average salary of employees - # of auctions it participated - donated $ to politicians? - …
Observatory of Public Spending neural networks: - two approaches: -
(“traditional”) neural network - deep neural network
Observatory of Public Spending TNN: - 2 hidden layers -
can’t handle 183 attributes - hence must use PCA first
Observatory of Public Spending TNN: - PCA - selected 24
continuous variables based on covariance matrix - PCA reduced 24 variables to 9 components (~70% of variance; all components w/ eigenvalue > 1)
Observatory of Public Spending TNN: - 9 components + 21
binary vars. - 80% training - w/ oversampling - 20% testing - boosting (10 models)
Observatory of Public Spending DNN: - 3 hidden layers -
hundreds of neurons - can handle all 183 variables - can handle complex relationships between the variables
Observatory of Public Spending DNN: - all 183 variables (no
PCA) - no oversampling - 80% training - 20% testing - 5-fold cross-validation
Observatory of Public Spending
Observatory of Public Spending how can we evaluate performance? -
accuracy (% of correct predictions overall) - recall (% of problems predicted to be problems) - precision (% of predicted problems that are problems)
Observatory of Public Spending how can we evaluate performance? -
accuracy (% of correct predictions overall) - recall (% of problems predicted to be problems) - precision (% of predicted problems that are problems)
Observatory of Public Spending results: - TNN precision: 0.24 -
DNN precision: 0.79 - huge difference! extra computational cost of DNN is worth it
Observatory of Public Spending to do: - improve recall -
0.58 w/ TNN - 0.26 w/ DNN - change the law - must allow gov not to contract w/ high risk companies
Observatory of Public Spending Ting Sun
[email protected]
Leonardo Sales
[email protected]
Observatory of Public Spending @tmarzagao thiagomarzagao.com