Dataset World Bank and UN to study International Development - Rostlab/DM_CS_WS_2016-17 GitHub Wiki
Dataset World Bank and UN to study International Development
- Proposer: Avradip Sen - avradips - [email protected]
- Votes:
- 🙋 @ishaanraj
- 🙋 @carockets
Summary
The World Bank and the UN have a vast amount of information regarding various development indicators. It would be interesting to see how multiple factors affect the growth of countries and also to find an efficient solution for development in the world.
Prediction Goals
Descriptive Analysis Goals
- Find unknown parameters and patterns related to GDP growth.
- Find patterns for poverty alleviation and how it is related to Health, Education, Technology and Industry.
- Find the effect of Foreign aid in Health, Education and Growth.
Predictive Analysis Tasks Goals
- Predict the growth of countries based on Current data.
- Predict the efficient utilization of resources in Health, Education, Technology and Industry for optimum growth.
Long Description
The World Bank and UN databases offer a lot of information regarding multiple parameters such as Health, Education, Economy, Environment, Science and Technology. I've listed some of the interesting fields below.
- Foreign AID – Effectiveness, Grants, School enrollments, Sanitation facilities, Poverty headcount.
- Health – Fertility rate, Life expectancy, Cause of Death, Immunization, Expenditure.
- Education – Literacy rate, Expenditure, Unemployment.
- Environment – Access to electricity, Renewable sources, CO2 emissions.
- Science and Technology – Internet usage, R&D expenditure, Patent applications.
- Infrastructure – Telephone users, Internet users, Availability and affordability of transportation.
- Poverty – Income shares, Urban and Rural poverty headcounts.
- Economy and Growth – GDP, Expenses, Exports vs Imports, Industry generation.
It would be interesting to see how this data correlates to each other and how countries can better utilize their resources to improve the social well being of its people.
Some of the main tasks involved would be to clean up the data as some of the data is missing as data starts becoming available for each country at different times in the past. Following that, we would have to find the factors we find interesting and mine the dataset for those factors.