DOC PREVIEW
UW-Madison ECE 539 - Prediction of Voting Patterns Based on Census and Demographic Data

This preview shows page 1-2-3 out of 9 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 9 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 9 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 9 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 9 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Slide 1AbstractVoting RepresentationsExperimental ProceduresExperimental ParametersExperiment 1 – Network StructureExperiment 2 - CoefficientsClassification ResultsConcluding RemarksPrediction of Voting Patterns Based on Census and Demographic DataAnalysis Performed by: Mike HeECE 539, Fall 2005AbstractAbstractPrediction of Voting Patterns in 2004 Prediction of Voting Patterns in 2004 Presidential ElectionPresidential ElectionMulti-Layer Perceptron, Back-PropagationMulti-Layer Perceptron, Back-PropagationBased on Demographic DataBased on Demographic DataPopulation SizePopulation SizeGender CompositionGender CompositionRacial CompositionRacial CompositionAge CompositionAge CompositionVoting RepresentationsVoting RepresentationsArea-Based Winner- Takes-All Map•Strict Red/Blue binary color coding•Can misrepresent actual popular opinionPopulation-Based Winner-Takes-All Cartogram•Counties resized to reflect actual population•More accurately reflects popular opinion•Illustrates high density of urban areas and tendency to vote DemocraticLinearly Shaded Vote-Percentage Map•Colors shaded according to vote percentages•Accurately portrays closeness of most races and political homogeneity throughout countryExperimental ProceduresExperimental ProceduresData Pre-ProcessingData Pre-ProcessingNetwork Structure DeterminationNetwork Structure Determination# of Hidden Layers, Neurons in Layers# of Hidden Layers, Neurons in LayersCoefficients DeterminationCoefficients DeterminationTraining, Training Error TestingTraining, Training Error TestingError from vote percentages, calling for Error from vote percentages, calling for candidatecandidateTesting on Testing Data SetTesting on Testing Data SetExperimental ParametersExperimental Parameters14 Features, 3 Outputs14 Features, 3 OutputsHyperbolic Tangent Activation Function for Hyperbolic Tangent Activation Function for Hidden LayersHidden LayersSigmoid Activation Function for Output Sigmoid Activation Function for Output LayerLayerLearning coefficient Learning coefficient αα=0.2=0.2Momentum coefficient Momentum coefficient μμ=0.5=0.5Experiment 1 – Network StructureExperiment 1 – Network StructureMany different structures tested according Many different structures tested according to total square errorto total square errorBest performers isolated for further testingBest performers isolated for further testingComparison of error across multiple trials Comparison of error across multiple trials between tested structuresbetween tested structuresWinner: 15 neurons in hidden layer, 4 Winner: 15 neurons in hidden layer, 4 hidden layershidden layersExperiment 2 - CoefficientsExperiment 2 - CoefficientsTo determine optimum To determine optimum αα and and μμDifferent sets of coefficients tested based Different sets of coefficients tested based on total square error as well as maximum on total square error as well as maximum square errorsquare errorChosen configuration:Chosen configuration:αα = 0.2, and = 0.2, and μμ = 0.5 = 0.5Classification ResultsClassification ResultsApplication of MLP to attempt to predict Application of MLP to attempt to predict which candidate will win each countywhich candidate will win each county100 training and prediction trials100 training and prediction trialsFor Wisconsin (training data), 77% For Wisconsin (training data), 77% classification rateclassification rateFor Minnesota (testing data), 75% For Minnesota (testing data), 75% classification rateclassification rateLess than 3% standard deviation in Less than 3% standard deviation in classification rate between trialsclassification rate between trialsConcluding RemarksConcluding RemarksImpressive overall predictive powerImpressive overall predictive powerRetains predictive power for different states:Retains predictive power for different states:Wisconsin and Minnesota similar demographically, Wisconsin and Minnesota similar demographically, different politicallydifferent politicallyPredictions based only on demographics – Predictions based only on demographics – innocuous data leads to powerful resultsinnocuous data leads to powerful resultsDemonstrates effectiveness of MLP’s as well as Demonstrates effectiveness of MLP’s as well as element of truth in common generalizations of element of truth in common generalizations of demographic voting tendenciesdemographic voting


View Full Document

UW-Madison ECE 539 - Prediction of Voting Patterns Based on Census and Demographic Data

Documents in this Course
Load more
Download Prediction of Voting Patterns Based on Census and Demographic Data
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Prediction of Voting Patterns Based on Census and Demographic Data and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Prediction of Voting Patterns Based on Census and Demographic Data 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?