Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries
Globally, both people and economic activity are increasingly concentrated in urban areas. Yet, for the vast majority of developing country cities, little is known about the granular spatial organization of such activity despite its key importance t...
| Main Authors: | , , , |
|---|---|
| Format: | Working Paper |
| Language: | English |
| Published: |
World Bank, Washington, DC
2022
|
| Subjects: | |
| Online Access: | http://documents.worldbank.org/curated/en/660611647960970611/Where-Are-All-the-Jobs-A-Machine-Learning-Approach-for-High-Resolution-Urban-Employment-Prediction-in-Developing-Countries http://hdl.handle.net/10986/37195 |
| id |
okr-10986-37195 |
|---|---|
| recordtype |
oai_dc |
| spelling |
okr-10986-371952022-04-07T17:50:10Z Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries Barzin, Samira Avner, Paolo Rentschler, Jun O’Clery, Neave DEVELOPMENT ECONOMICS URBAN ECONOMICS CITIES FIRM LOCATIONS BIG DATA SATELITE DATA COMPUTATIONAL METHODS MACHINE LEARNING Globally, both people and economic activity are increasingly concentrated in urban areas. Yet, for the vast majority of developing country cities, little is known about the granular spatial organization of such activity despite its key importance to policy and urban planning. This paper adapts a machine learning based algorithm to predict the spatial distribution of employment using input data from open access sources such as Open Street Map and Google Earth Engine. The algorithm is trained on 14 test cities, ranging from Buenos Aires in Argentina to Dakar in Senegal. A spatial adaptation of the random forest algorithm is used to predict within-city cells in the 14 test cities with extremely high accuracy (R- squared greater than 95 percent), and cells in out-of-sample ”unseen” cities with high accuracy (mean R-squared of 63 percent). This approach uses open data to produce high resolution estimates of the distribution of urban employment for cities where such information does not exist, making evidence-based planning more accessible than ever before. 2022-03-23T14:48:55Z 2022-03-23T14:48:55Z 2022-03 Working Paper http://documents.worldbank.org/curated/en/660611647960970611/Where-Are-All-the-Jobs-A-Machine-Learning-Approach-for-High-Resolution-Urban-Employment-Prediction-in-Developing-Countries http://hdl.handle.net/10986/37195 English Policy Research Working Paper;9979 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo World Bank World Bank, Washington, DC Policy Research Working Paper Publications & Research |
| repository_type |
Digital Repository |
| institution_category |
Foreign Institution |
| institution |
Digital Repositories |
| building |
World Bank Open Knowledge Repository |
| collection |
World Bank |
| language |
English |
| topic |
DEVELOPMENT ECONOMICS URBAN ECONOMICS CITIES FIRM LOCATIONS BIG DATA SATELITE DATA COMPUTATIONAL METHODS MACHINE LEARNING |
| spellingShingle |
DEVELOPMENT ECONOMICS URBAN ECONOMICS CITIES FIRM LOCATIONS BIG DATA SATELITE DATA COMPUTATIONAL METHODS MACHINE LEARNING Barzin, Samira Avner, Paolo Rentschler, Jun O’Clery, Neave Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries |
| relation |
Policy Research Working Paper;9979 |
| description |
Globally, both people and economic
activity are increasingly concentrated in urban areas. Yet,
for the vast majority of developing country cities, little
is known about the granular spatial organization of such
activity despite its key importance to policy and urban
planning. This paper adapts a machine learning based
algorithm to predict the spatial distribution of employment
using input data from open access sources such as Open
Street Map and Google Earth Engine. The algorithm is trained
on 14 test cities, ranging from Buenos Aires in Argentina to
Dakar in Senegal. A spatial adaptation of the random forest
algorithm is used to predict within-city cells in the 14
test cities with extremely high accuracy (R- squared greater
than 95 percent), and cells in out-of-sample ”unseen” cities
with high accuracy (mean R-squared of 63 percent). This
approach uses open data to produce high resolution estimates
of the distribution of urban employment for cities where
such information does not exist, making evidence-based
planning more accessible than ever before. |
| format |
Working Paper |
| author |
Barzin, Samira Avner, Paolo Rentschler, Jun O’Clery, Neave |
| author_facet |
Barzin, Samira Avner, Paolo Rentschler, Jun O’Clery, Neave |
| author_sort |
Barzin, Samira |
| title |
Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries |
| title_short |
Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries |
| title_full |
Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries |
| title_fullStr |
Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries |
| title_full_unstemmed |
Where Are All the Jobs ? : A Machine Learning Approach for High Resolution Urban Employment Prediction in Developing Countries |
| title_sort |
where are all the jobs ? : a machine learning approach for high resolution urban employment prediction in developing countries |
| publisher |
World Bank, Washington, DC |
| publishDate |
2022 |
| url |
http://documents.worldbank.org/curated/en/660611647960970611/Where-Are-All-the-Jobs-A-Machine-Learning-Approach-for-High-Resolution-Urban-Employment-Prediction-in-Developing-Countries http://hdl.handle.net/10986/37195 |
| _version_ |
1764486700731465728 |