Indicators

Education, Experience, Safety...
ⓧ
2
Indicator Weights
Indicator importance is determined by Random Forest training. Learn More
Population
Education
Work Experience
Youth Poverty
Adult Poverty
Senior Poverty
Location

Enter zipcode...

GO
About Prototype

Community Forecasting
Prototype developed during Data Visualization studies at Georgia Tech. Latest work resides at model.earth.
ⓧ
⧁
⇗


Getting Started



Predictors of Increased Poverty


The model will set default weights using the Random Forest Classifier feature importance based on an increase of 2% or more for the selected indicator.
Random Forest Classifier

Values are per 1,000 individuals. Disclaimer: Data is based on projections which is prone to error.
2016 predicting 2017 Poverty
For model training, a "y" column value of 1 indicated zip codes where poverty increased in 2017 after increasing or remaining steady from 2015 to 2016.


Best Params: max depth: 8; n-estimators: 100
Accuracy before tuning: 69%.  Accuracy after tuning: 71%.






 
ⓧ
1
Choose Area of Focus
We'll generate a map with clusters corresponding to your theme.

Where would you like
to focus your efforts?

Education Needs
Work Experience Needs
Youth Below Poverty Level
Adults Below Poverty Level
Seniors Below Poverty Level
NEXT