Description

• Contribute to the further development and execution of an on-going methodological research program on small area estimation (SAE), specifically to answer open research questions regarding the integration of georeferenced census/survey data with high-resolution satellite imagery, geospatial data, as well as georeferenced alternative data sources, including call detail records (CDRs), administrative records, and citizen-generated data, to obtain sub-national, hyperlocal estimates of sustainable development outcomes, including, but not limited to, monetary poverty, consumption, income, and wealth. 
  
• Contribute to ongoing research that aims to identify the optimal volume of and approach to georeferenced ground data collection through surveys and censuses in order to provide the requisite training data for remotely sensed, hyperlocal estimates of sustainable development outcomes that are obtained by integrating georeferenced census/survey data with high-resolution satellite imagery, and geospatial data (henceforth referred to as integrated survey/census-geospatial data applications). 
  
• Related workstreams will be to (a) validate the use of survey-to-census imputation to produce reliable predictions that can in turn be used as training data; (ii) identify the recommended estimation techniques, including machine learning approaches, for integrated survey/census-geospatial data applications; and (iii) determine the optimal scope and type of geospatial features that should be used in these applications. These efforts will culminate in co-authored working papers, journal articles, and methodological guidelines.
  
• Apply knowledge from the aforementioned research program and the latest developments in data integration and machine learning to provide methodological guidance to World Bank-supported integrated survey/census-geospatial data applications.
  
• Produce geospatial rasters that document the extent of variation in subnational levels and changes in selected sustainable development outcomes in a minimum of five countries at different income levels and stages of structural transformation. These products will be based on the integration of survey/census and geospatial data sources to produce subnational estimates of poverty, mean household consumption/income, and household wealth, including estimates of uncertainty, both at 5-kilometer pixel-level and at the finest level of administrative sub-division in that country, generated at least two points in time separated by approximately 10 years. The process for producing these estimates must be aligned with the forthcoming World Bank policy on data quality, and The Consultant will therefore test, evaluate, validate and verify different models, consult with stakeholders, and produce careful and thorough documentation.   
• Perform any other related assignment, as requested by the supervisor. 

Selection Criteria

•A minimum of 5 years of relevant professional experience, or equivalent combination of education and experience

•Demonstrated expertise in data integration, preferably with respect to estimating poverty and welfare, machine learning, and small area estimation.

•Excellent English writing and communication skills.

World Bank Group Core Competencies

We are proud to be an equal opportunity and inclusive employer with a dedicated and committed workforce, and do not discriminate based on gender, gender identity, religion, race, ethnicity, sexual orientation, or disability.

Learn more about working at the World Bank and IFC, including our values and inspiring stories.