https://github.com/shahardekel/poverty-prediction

https://github.com/shahardekel/poverty-prediction

Last synced: about 16 hours ago
JSON representation

• Host: GitHub
• URL: https://github.com/shahardekel/poverty-prediction
• Owner: shahardekel
• Created: 2023-11-14T12:43:49.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2023-11-14T12:49:30.000Z (12 months ago)
• Last Synced: 2023-11-14T13:40:02.400Z (12 months ago)
• Language: Jupyter Notebook
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Poverty-Prediction

Many social programs have a hard time making sure the right people are given enough aid.


It’s especially tricky when a program focuses on the poorest segment of the population.


The world’s poorest typically can’t provide the necessary income and expense records to prove that they qualify.



In Latin America, one popular method uses an algorithm to verify income qualification, It’s called the Proxy Means Test (or PMT).


With PMT, agencies use a model that considers a family’s observable household attributes like the material of their walls and ceiling, or the assets found in the home to classify them and predict their level of need.



While this is an improvement, accuracy remains a problem as the region’s population grows and poverty declines.


there is a belief that new methods beyond traditional econometrics, based on a dataset of Costa Rican household characteristics, might help improve PMT’s performance.



The data contains 142 columns, with core columns:

- Id - a unique identifier for each row.

- Target - the target is an ordinal variable indicating groups of income levels.

        1 = extreme poverty

        2 = moderate poverty

        3 = vulnerable households

        4 = non vulnerable households

- idhogar - this is a unique identifier for each household. This can be used to create household-wide features, etc. All rows in a given household will have a matching value for this identifier.

- parentesco1 - indicates if this person is the head of the household.

Full data available here 

https://www.kaggle.com/competitions/costa-rican-household-poverty-prediction/data

The workflow in this project:

- import the data

- clean the data

- find relevant parameters 

- create a model

- optimize the model 

- fit and test the model

Accuracy result- 92.25%