Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134667524> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3134667524 abstract "We propose a novel conditional GANs architecture for crime (robberies) prediction in Bogota, capital city of Colombia. The model uses several layers of ConvLSTM neural nets in both the generative and the discriminatory networks. We further condition on past crime intensity maps, weekdays, and holidays. The trained network is able to capture spatiotemporal patterns and outperforms state-of-the-art predictive models such as spatiotemporal Poisson point process, as well as other models trained with the same dataset. Model's accuracy reaches an area under the Hit Rate - Percentage Area Covered by Hotspots curve of 0.86. However, our predictions suggest that there is a potential bias with heterogeneous effects on vulnerable populations. We address the fairness consequence of this model in low income vs. high income residents by estimating a calibration test conditional to these protected variables. Finally, we introduce a fairness - accuracy balancing technique that quantifies the tradeoffs between accuracy and fairness in this type of models. This technique notably reduces bias with a marginal effect on accuracy." @default.
- W3134667524 created "2021-03-15" @default.
- W3134667524 creator A5020294239 @default.
- W3134667524 creator A5053721081 @default.
- W3134667524 creator A5055381811 @default.
- W3134667524 creator A5069752509 @default.
- W3134667524 creator A5089134443 @default.
- W3134667524 date "2020-11-05" @default.
- W3134667524 modified "2023-10-16" @default.
- W3134667524 title "Accuracy and Fairness in a Conditional Generative Adversarial Model of Crime Prediction" @default.
- W3134667524 cites W1485009520 @default.
- W3134667524 cites W1971935825 @default.
- W3134667524 cites W2008625160 @default.
- W3134667524 cites W2099471712 @default.
- W3134667524 cites W2123906784 @default.
- W3134667524 cites W2164891102 @default.
- W3134667524 cites W2529251251 @default.
- W3134667524 cites W2530395818 @default.
- W3134667524 cites W2804697534 @default.
- W3134667524 cites W2805373902 @default.
- W3134667524 cites W2902038708 @default.
- W3134667524 cites W2909023669 @default.
- W3134667524 cites W2962848907 @default.
- W3134667524 cites W2963178340 @default.
- W3134667524 cites W3123374861 @default.
- W3134667524 cites W3126362025 @default.
- W3134667524 doi "https://doi.org/10.1109/besc51023.2020.9348315" @default.
- W3134667524 hasPublicationYear "2020" @default.
- W3134667524 type Work @default.
- W3134667524 sameAs 3134667524 @default.
- W3134667524 citedByCount "2" @default.
- W3134667524 countsByYear W31346675242021 @default.
- W3134667524 crossrefType "proceedings-article" @default.
- W3134667524 hasAuthorship W3134667524A5020294239 @default.
- W3134667524 hasAuthorship W3134667524A5053721081 @default.
- W3134667524 hasAuthorship W3134667524A5055381811 @default.
- W3134667524 hasAuthorship W3134667524A5069752509 @default.
- W3134667524 hasAuthorship W3134667524A5089134443 @default.
- W3134667524 hasConcept C105795698 @default.
- W3134667524 hasConcept C111919701 @default.
- W3134667524 hasConcept C119857082 @default.
- W3134667524 hasConcept C149782125 @default.
- W3134667524 hasConcept C154945302 @default.
- W3134667524 hasConcept C165838908 @default.
- W3134667524 hasConcept C2524010 @default.
- W3134667524 hasConcept C28719098 @default.
- W3134667524 hasConcept C33923547 @default.
- W3134667524 hasConcept C39890363 @default.
- W3134667524 hasConcept C41008148 @default.
- W3134667524 hasConcept C50644808 @default.
- W3134667524 hasConcept C98045186 @default.
- W3134667524 hasConceptScore W3134667524C105795698 @default.
- W3134667524 hasConceptScore W3134667524C111919701 @default.
- W3134667524 hasConceptScore W3134667524C119857082 @default.
- W3134667524 hasConceptScore W3134667524C149782125 @default.
- W3134667524 hasConceptScore W3134667524C154945302 @default.
- W3134667524 hasConceptScore W3134667524C165838908 @default.
- W3134667524 hasConceptScore W3134667524C2524010 @default.
- W3134667524 hasConceptScore W3134667524C28719098 @default.
- W3134667524 hasConceptScore W3134667524C33923547 @default.
- W3134667524 hasConceptScore W3134667524C39890363 @default.
- W3134667524 hasConceptScore W3134667524C41008148 @default.
- W3134667524 hasConceptScore W3134667524C50644808 @default.
- W3134667524 hasConceptScore W3134667524C98045186 @default.
- W3134667524 hasLocation W31346675241 @default.
- W3134667524 hasOpenAccess W3134667524 @default.
- W3134667524 hasPrimaryLocation W31346675241 @default.
- W3134667524 hasRelatedWork W11175205 @default.
- W3134667524 hasRelatedWork W115308 @default.
- W3134667524 hasRelatedWork W1678066 @default.
- W3134667524 hasRelatedWork W5518722 @default.
- W3134667524 hasRelatedWork W7432053 @default.
- W3134667524 hasRelatedWork W8021486 @default.
- W3134667524 hasRelatedWork W8726526 @default.
- W3134667524 hasRelatedWork W8821115 @default.
- W3134667524 hasRelatedWork W9321062 @default.
- W3134667524 hasRelatedWork W2217443 @default.
- W3134667524 isParatext "false" @default.
- W3134667524 isRetracted "false" @default.
- W3134667524 magId "3134667524" @default.
- W3134667524 workType "article" @default.